© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59085
    Prev
    Next
    INDEX
    Explanations

    go for / go on / go into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollo
    -0.10
     Tat
    -0.10
    дж
    -0.09
    idad
    -0.09
    ella
    -0.08
    opr
    -0.08
     "$(
    -0.08
    ifying
    -0.08
     hierarchy
    -0.08
     tat
    -0.08
    POSITIVE LOGITS
    æ²¥
    0.10
    çĸµ
    0.10
    äºĽä»Ģä¹Ī
    0.09
    åħ¬åı¸åľ¨
    0.09
    娣
    0.09
    çªĿ
    0.09
    ëĦ¤
    0.09
    äº
    0.09
    ç³ł
    0.08
    inspace
    0.08
    Activations Density 0.046%

    No Known Activations