© 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. 36303
    Prev
    Next
    INDEX
    Explanations

    Choice Award

    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
    çĬĬ
    -0.09
    éĴį
    -0.08
    æĥ³æĥ³
    -0.08
    æ¯ĽåŃĶ
    -0.08
    ancell
    -0.08
    antis
    -0.08
    çķĪ
    -0.08
    çļĦ人æĿ¥è¯´
    -0.08
     Colbert
    -0.08
    åŃĽ
    -0.08
    POSITIVE LOGITS
    çĭ¬è§Ĵ
    0.10
    inger
    0.09
    aram
    0.09
    ä¸Ńå¤ĸ
    0.08
    /at
    0.08
    appropri
    0.08
    å¥
    0.08
    ãģ¨ãģĦãģĨãģĵãģ¨ãģ§
    0.08
    è¿Ļ份
    0.08
    ENU
    0.08
    Activations Density 0.041%

    No Known Activations