© 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. 11721
    Prev
    Next
    INDEX
    Explanations

    assessment tasks or methods

    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
    é¢ł
    -0.10
    æłĵ
    -0.09
    iated
    -0.09
    FI
    -0.09
    侮辱
    -0.08
    mong
    -0.08
     Chew
    -0.08
    梳
    -0.08
     aud
    -0.08
    ius
    -0.08
    POSITIVE LOGITS
    åĪ¶åº¦æĶ¹éĿ©
    0.12
    èĢĥæł¸
    0.11
    istica
    0.10
    åıijçİ°èĩªå·±
    0.10
    ä½ĵ系建设
    0.10
    æĸ¹å¼ı
    0.09
    _TRANSL
    0.09
     Homeland
    0.09
    è¯Ħä»·
    0.09
    对æĸ¹
    0.08
    Activations Density 0.033%

    No Known Activations