© 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. 62068
    Prev
    Next
    INDEX
    Explanations

    Kuhinjica

    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
    uary
    -0.10
    robe
    -0.09
    Echo
    -0.09
    Ä°K
    -0.09
    æľĪç»ı
    -0.08
    _geom
    -0.08
    ÖĦ
    -0.08
    çĩĬ
    -0.08
    obe
    -0.08
    chant
    -0.08
    POSITIVE LOGITS
    æĹłæĥħ
    0.09
    éĩįå¡ij
    0.09
    ä¹ĭ声
    0.09
    igli
    0.09
    éĴ´
    0.09
    ä¸Ģ头
    0.09
    è¯ĥ
    0.08
    éĩįç»Ħ
    0.08
    ç»ĦåĽ¢
    0.08
    åįĸç»Ļ
    0.08
    Activations Density 0.088%

    No Known Activations