© 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. 61530
    Prev
    Next
    INDEX
    Explanations

    indexing and indexes

    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
    éĩįä¸Ń
    -0.10
    åIJĮæĥħ
    -0.09
    .named
    -0.09
    潦
    -0.08
    æ¯ķ
    -0.08
    éĸĭ
    -0.08
    çķ¢
    -0.08
    itled
    -0.08
    空ä¸Ń
    -0.08
     Saunders
    -0.08
    POSITIVE LOGITS
    çģµéŃĤ
    0.09
    IBILITY
    0.09
    éĴ¥åĮĻ
    0.09
    å¿ĥçģµ
    0.09
    _ENTRIES
    0.08
    æ¢Ĺ
    0.08
    _rl
    0.08
    blas
    0.08
    INCT
    0.08
    ÅĽni
    0.08
    Activations Density 0.020%

    No Known Activations