© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9047
    Prev
    Next
    INDEX
    Explanations

    analytic and analytical

    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
    idon
    -0.09
    çĦī
    -0.09
    .mj
    -0.08
    lain
    -0.08
    åIJ¯
    -0.08
    çĺĮ
    -0.08
    /how
    -0.07
    æķĻ导
    -0.07
     retrie
    -0.07
     Turnbull
    -0.07
    POSITIVE LOGITS
    屿
    0.11
    ìĭ¬
    0.10
    å¯ĨåĪĩåħ³æ³¨
    0.10
    åĨįéĢł
    0.10
    仪表
    0.09
    èµ°å¾Ĺ
    0.09
    è·ĿéĽ¢
    0.09
    åģı离
    0.09
    inx
    0.09
    èĮ§
    0.09
    Activations Density 0.030%

    No Known Activations