© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38049
    Prev
    Next
    INDEX
    Explanations

    python process or module names

    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
    åĸĦäºİ
    -0.10
    æľ¬æĬ¥
    -0.10
    eree
    -0.10
    itched
    -0.10
    åIJijè®°èĢħ
    -0.09
    漪
    -0.09
    ä¸Ģåı£æ°Ķ
    -0.09
    angler
    -0.09
    ç¼Ł
    -0.09
    ovich
    -0.08
    POSITIVE LOGITS
    èĵŁ
    0.09
    raz
    0.09
     Offline
    0.09
    éĹª
    0.08
    InitialState
    0.08
     Med
    0.08
    è¾¹
    0.08
    åºĵéĩĮ
    0.08
    离åİ»
    0.08
    .setError
    0.08
    Activations Density 0.024%

    No Known Activations