© 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. 61379
    Prev
    Next
    INDEX
    Explanations

    preceded by, precedential, derivative

    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
    rear
    -0.09
    imest
    -0.09
    à¸Ļาà¸Ļ
    -0.09
    ä¸ĭåįĬ
    -0.08
     hostages
    -0.08
    keeper
    -0.08
     Turing
    -0.08
     dad
    -0.08
    ular
    -0.08
    /of
    -0.08
    POSITIVE LOGITS
    åĻ©
    0.10
    lok
    0.09
    é¢Ħå¤ĩ
    0.09
    ibilit
    0.09
    éģ®
    0.08
    oky
    0.08
    æİĮ声
    0.08
    angelo
    0.08
    åľ¨æѤ
    0.08
    æİīèIJ½
    0.08
    Activations Density 0.001%

    No Known Activations