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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 84053
    Prev
    Next
    INDEX
    Explanations

    potential

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    不适合
    -0.07
    世界级
    -0.07
    𝙼
    -0.07
     Knight
    -0.06
    ascular
    -0.06
     canadian
    -0.06
     coolest
    -0.06
    変わって
    -0.06
    Brit
    -0.06
     amid
    -0.06
    POSITIVE LOGITS
    TURN
    0.08
     RestClient
    0.08
     stor
    0.07
     sentinel
    0.07
     nova
    0.07
    Results
    0.07
    “You
    0.07
    	JSONObject
    0.07
     Kodi
    0.07
    etsk
    0.07
    Activations Density 0.028%

    No Known Activations