© 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. 50753
    Prev
    Next
    INDEX
    Explanations

    synth

    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
     bif
    -0.09
     çe
    -0.08
     undergo
    -0.08
    拥抱
    -0.07
     Cleaning
    -0.07
    עצב
    -0.07
    西甲
    -0.07
    这一切
    -0.07
     bitcoin
    -0.07
     '|
    -0.07
    POSITIVE LOGITS
     Athen
    0.07
     المست
    0.07
    瑟
    0.07
    因为你
    0.07
    肠
    0.07
     player
    0.07
    .getUsername
    0.07
    研究所
    0.06
     В
    0.06
    铁
    0.06
    Activations Density 0.005%

    No Known Activations