© 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. 23951
    Prev
    Next
    INDEX
    Explanations

    C

    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
     shootout
    -0.07
    htar
    -0.07
    שלום
    -0.07
    unfold
    -0.07
    URITY
    -0.07
     comun
    -0.07
     amnesty
    -0.07
    .Compare
    -0.06
     getAll
    -0.06
     utrecht
    -0.06
    POSITIVE LOGITS
     Vegetable
    0.07
     negatively
    0.07
     Damn
    0.07
    Proveedor
    0.06
     кол
    0.06
     Think
    0.06
    停止
    0.06
     המרכזי
    0.06
    درجة
    0.06
     المزيد
    0.06
    Activations Density 0.001%

    No Known Activations