© 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. 56502
    Prev
    Next
    INDEX
    Explanations

    numbers and names with suffixes

    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
     Feinstein
    -0.10
    plements
    -0.09
    åĪĨå·¥
    -0.09
    omid
    -0.09
    entine
    -0.09
    iginal
    -0.09
    AndServe
    -0.09
    otics
    -0.08
    丧失
    -0.08
    ä»»æĢ§
    -0.08
    POSITIVE LOGITS
    éĺĹ
    0.11
    éĴµ
    0.10
    åĴĢ
    0.09
    è°´
    0.09
    suite
    0.09
    urance
    0.08
    æİĩ
    0.08
    ouver
    0.08
    ered
    0.08
    cip
    0.08
    Activations Density 0.818%

    No Known Activations