© 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. 19-RESID-POST-AA
    11. 110342
    Prev
    Next
    INDEX
    Explanations

    Everything in between

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    宁静
    -0.08
    )this
    -0.07
    .BackColor
    -0.07
    .GetLength
    -0.07
    reb
    -0.07
    /></
    -0.07
     coherent
    -0.07
    真正的
    -0.06
    ものを
    -0.06
    因为它
    -0.06
    POSITIVE LOGITS
    XXX
    0.08
    🎌
    0.07
    ival
    0.07
    zos
    0.07
    卡通
    0.07
    viron
    0.07
     yt
    0.06
    戬
    0.06
     participação
    0.06
    Production
    0.06
    Activations Density 0.096%

    No Known Activations