© 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. 73998
    Prev
    Next
    INDEX
    Explanations

    Numerical data

    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
    öt
    -0.07
     CLEAN
    -0.07
     hotel
    -0.07
    臺灣
    -0.06
    efeller
    -0.06
     MATLAB
    -0.06
     MacDonald
    -0.06
    -mounted
    -0.06
     Icelandic
    -0.06
    áln
    -0.06
    POSITIVE LOGITS
     anomalies
    0.07
    消息称
    0.07
    칩
    0.07
    作风
    0.07
     successors
    0.07
     świad
    0.07
     muzzle
    0.07
    Unsupported
    0.06
     fired
    0.06
    (pt
    0.06
    Activations Density 0.020%

    No Known Activations