© 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. 17351
    Prev
    Next
    INDEX
    Explanations

    nerd

    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
     Simon
    -0.07
    ӡ
    -0.07
    ,\"
    -0.07
    ptest
    -0.07
    <Student
    -0.06
    bio
    -0.06
     assignment
    -0.06
     Maurice
    -0.06
     march
    -0.06
    魔术
    -0.06
    POSITIVE LOGITS
    ington
    0.08
     Webcam
    0.07
    业内人士
    0.07
    ابل
    0.07
     penetrate
    0.07
    بالغ
    0.07
    טה
    0.07
     كرة
    0.07
    _primary
    0.07
    نسب
    0.07
    Activations Density 0.005%

    No Known Activations