© 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. 38682
    Prev
    Next
    INDEX
    Explanations

    commissioners and figures

    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
    ç¾İ人
    -0.09
    ç¾¤å²Ľ
    -0.09
    eda
    -0.09
    æĬķ
    -0.09
    enos
    -0.09
    æ´Ĺ涤
    -0.09
    éĩįç»Ħ
    -0.08
    èīºäºº
    -0.08
    ItemType
    -0.08
    æŃ£å½ĵ
    -0.08
    POSITIVE LOGITS
    æ»ĩ
    0.10
    iron
    0.10
    鸽
    0.09
    çĽĴ
    0.09
    éĢł
    0.09
    éĢĴ
    0.09
    romium
    0.09
    vä
    0.08
    è¿Ļæł·æīįèĥ½
    0.08
    ucs
    0.08
    Activations Density 0.003%

    No Known Activations