© 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. 11910
    Prev
    Next
    INDEX
    Explanations

    dkim-filter, headers, messages

    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
    嵬
    -0.09
    ç½½
    -0.08
    èĪĴæľį
    -0.08
    æī¶
    -0.08
    ound
    -0.08
    çł´
    -0.08
    çĸı
    -0.08
    央
    -0.08
    REM
    -0.08
    éģģ
    -0.08
    POSITIVE LOGITS
    åĪ°æĿ¥
    0.11
    é»ı
    0.09
    ivist
    0.09
    åı¯ä¿¡
    0.09
    ä½ıåľ¨
    0.09
    æĭĸ延
    0.09
     Gret
    0.09
    oland
    0.09
    åĨį说
    0.09
    ISTS
    0.08
    Activations Density 0.090%

    No Known Activations