© 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. 34090
    Prev
    Next
    INDEX
    Explanations

    asking questions, frequently asked

    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
    éĿ¢çĻ½
    -0.08
    çļĦåľ°
    -0.08
    éĩĩ
    -0.08
    isan
    -0.08
    ofs
    -0.08
    راء
    -0.08
     Gros
    -0.08
    ä¸Ģæŀļ
    -0.08
     Hide
    -0.07
    大èĥĨ
    -0.07
    POSITIVE LOGITS
    æĥ³çŁ¥éģĵ
    0.13
    éĹ®æĪij
    0.11
    询éĹ®
    0.11
    asks
    0.11
    éĹ®
    0.11
    家éķ¿ä»¬
    0.10
    éĹ®éģĵ
    0.10
    æĹłæķ°æ¬¡
    0.10
    è©¢
    0.10
    ç»į
    0.10
    Activations Density 0.083%

    No Known Activations