© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 49470
    Prev
    Next
    INDEX
    Explanations

    remorse

    np_max-act · gemini-2.0-flash
    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
     dzie
    -0.07
    坩
    -0.07
     speaks
    -0.07
    祭祀
    -0.07
    行业内
    -0.06
    陡
    -0.06
     PROF
    -0.06
    .SizeF
    -0.06
    危險
    -0.06
     Independ
    -0.06
    POSITIVE LOGITS
    middle
    0.07
    fstream
    0.07
     formula
    0.07
    Ip
    0.07
    jos
    0.07
    -box
    0.07
    买
    0.07
    的比例
    0.07
    电量
    0.07
    EI
    0.07
    Activations Density 0.005%

    No Known Activations