© 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. 5183
    Prev
    Next
    INDEX
    Explanations

    raptor

    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
    è¢ĭåŃIJ
    -0.10
    ARING
    -0.09
    peg
    -0.09
    DIRECT
    -0.09
    ìŀ¥
    -0.09
    奶èĮ¶
    -0.09
    PING
    -0.09
    ars
    -0.09
    æīĵ好
    -0.08
    ared
    -0.08
    POSITIVE LOGITS
    itious
    0.09
    çĦ¶æĺ¯
    0.09
    å·¥å§Ķ
    0.09
    ILON
    0.09
    antly
    0.08
    æľĢ好æĺ¯
    0.08
     Crit
    0.08
    à¸Ńà¸ĩ
    0.08
    bé
    0.08
     данном
    0.08
    Activations Density 0.002%

    No Known Activations