© 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. 17022
    Prev
    Next
    INDEX
    Explanations

    batsman

    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
    æī¯
    -0.10
    dden
    -0.10
    æĢ¡
    -0.10
    çĽijå¯Ł
    -0.09
    åİ»çľĭ
    -0.09
    æīİæł¹
    -0.09
    andest
    -0.09
    é¢ģ
    -0.09
    _routes
    -0.09
    ofire
    -0.09
    POSITIVE LOGITS
    éĶ¤
    0.09
     seated
    0.09
    rape
    0.09
     styl
    0.08
     bare
    0.08
    (OP
    0.08
    ısı
    0.08
    çķ¸
    0.08
     Riley
    0.08
    rim
    0.08
    Activations Density 0.228%

    No Known Activations