© 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. 61995
    Prev
    Next
    INDEX
    Explanations

    types of entities or classifications

    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
    æŁ¬
    -0.11
    oeff
    -0.09
    ligt
    -0.09
    ç»IJ
    -0.09
    çŀĭ
    -0.08
     decades
    -0.08
    çĿĩ
    -0.08
    á»įn
    -0.08
    éħ±
    -0.08
    ä¸įè´Ł
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.10
    stk
    0.10
    满
    0.10
    “
    0.09
    åIJį为
    0.09
    潸
    0.08
    诸å¦Ĥ
    0.08
    ç´«
    0.08
     Hort
    0.08
    ãģĴ
    0.08
    Activations Density 0.546%

    No Known Activations