© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8321
    Prev
    Next
    INDEX
    Explanations

    Indian Institute of Science

    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
    ÑĢаÑĤ
    -0.08
    æ°ijå¿ĥ
    -0.08
    orsk
    -0.08
    ç«¥
    -0.08
    oya
    -0.08
    ãĥ«ãĥ¼
    -0.07
    adius
    -0.07
    ark
    -0.07
    çŁ¥éģĵ
    -0.07
    ba
    -0.07
    POSITIVE LOGITS
    Ðķ
    0.14
    ðĿijĴ
    0.13
    à§ĩ
    0.13
    à¥ĩà¤
    0.13
    ãģĪ
    0.12
     Enterprises
    0.12
    åĦ¿
    0.12
    E
    0.12
    _e
    0.12
     E
    0.12
    Activations Density 0.373%

    No Known Activations