© 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. 11850
    Prev
    Next
    INDEX
    Explanations

    list separators

    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
    æ³ģ
    -0.11
    æĪĸèĢħæĺ¯
    -0.10
    IGO
    -0.09
    æĦĨ
    -0.09
    çĶļèĩ³æĺ¯
    -0.09
    åĨµä¸Ķ
    -0.09
    æĪĸæĺ¯
    -0.09
    æĪijä¹Ł
    -0.09
    alon
    -0.09
    ekt
    -0.08
    POSITIVE LOGITS
    ;
    0.14
     --
    0.10
    --
    0.09
    ï¼Ľ
    0.09
    oracle
    0.08
     ;
    0.08
    --;
    0.08
    ws
    0.08
    示æĦı
    0.08
    ноÑģÑĤей
    0.08
    Activations Density 0.117%

    No Known Activations