© 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. 17010
    Prev
    Next
    INDEX
    Explanations

    tongue

    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
    anter
    -0.10
    IMUM
    -0.09
    /disable
    -0.09
    anje
    -0.09
    lut
    -0.08
    å¼Ģåı£
    -0.08
    头çļ®
    -0.08
    å¿ĥå¢ĥ
    -0.08
    æ®ĥ
    -0.08
    aved
    -0.08
    POSITIVE LOGITS
    LESS
    0.12
    auge
    0.12
    less
    0.10
    lessly
    0.09
    maid
    0.09
    åı¨
    0.09
    -speaking
    0.09
    è¿Ļæł·çļĦè¯Ŀ
    0.08
    flower
    0.08
    ÑĪиб
    0.08
    Activations Density 0.015%

    No Known Activations