© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 24634
    Prev
    Next
    INDEX
    Explanations

    Regret/problems

    np_max-act · gemini-2.0-flash

    statements describing user-caused mistakes or accidental actions followed by regret and a desire to fix or undo the problem.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🙌
    -0.07
    ullet
    -0.07
    小
    -0.06
    体
    -0.06
    ǿ
    -0.06
     lParam
    -0.06
     senza
    -0.06
    HITE
    -0.06
     mayor
    -0.06
    MENU
    -0.06
    POSITIVE LOGITS
     evidenced
    0.08
     Divide
    0.08
     Bundes
    0.08
    /Page
    0.07
    ={()=>
    0.07
    موضوع
    0.07
    无数次
    0.07
     Primer
    0.07
     CWE
    0.07
     در
    0.07
    Activations Density 0.093%

    No Known Activations