© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 7-RESID-POST-AA
    11. 83237
    Prev
    Next
    INDEX
    Explanations

    assistant

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -depth
    -0.07
     regression
    -0.07
    	r
    -0.07
     распространен
    -0.06
    .cost
    -0.06
    ,r
    -0.06
    🏋
    -0.06
    ifecycle
    -0.06
    -pre
    -0.06
    _cc
    -0.06
    POSITIVE LOGITS
    עצמ
    0.07
    掌声
    0.07
     absorbing
    0.07
    一带
    0.07
     frantic
    0.07
    Rain
    0.07
    ניסי
    0.06
     سابق
    0.06
    产能
    0.06
    اته
    0.06
    Activations Density 0.019%

    No Known Activations