© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11256
    Prev
    Next
    INDEX
    Explanations

    Mohamed, Mohigans, mohawk

    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
    ãģĹãĤĩãģĨ
    -0.10
    noon
    -0.09
    urate
    -0.09
    èĬĤå¥ı
    -0.09
    owing
    -0.09
    éĿ¡
    -0.08
    æľ¬ç½ij
    -0.08
    orm
    -0.08
    ãĤīãģĦ
    -0.08
     Benson
    -0.08
    POSITIVE LOGITS
    antly
    0.10
    é£
    0.10
    ments
    0.09
    ãģıãĤĭ
    0.09
    mina
    0.09
    åĽłèĢĮ
    0.09
    çĸ¹
    0.08
    .elem
    0.08
    igg
    0.08
     Punch
    0.08
    Activations Density 0.009%

    No Known Activations