© 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. 32544
    Prev
    Next
    INDEX
    Explanations

    take something literally

    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
    çķĻå®Ī
    -0.08
    导èĩ´
    -0.08
    两æĿ¡
    -0.08
    åij½åIJį为
    -0.08
    ç«Ļèµ·æĿ¥
    -0.08
    .ind
    -0.08
    á»±a
    -0.08
    家åĽŃ
    -0.08
    _wrap
    -0.08
    aldi
    -0.08
    POSITIVE LOGITS
    ylon
    0.09
    inia
    0.09
    æµĨ
    0.09
    åIJ¬åIJ¬
    0.08
    bum
    0.08
    inke
    0.08
    ynn
    0.08
    çķª
    0.08
    ä¸īåĪĨ
    0.08
    æħİ
    0.08
    Activations Density 0.011%

    No Known Activations