© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10571
    Prev
    Next
    INDEX
    Explanations

    practice

    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
    è´¨éĩı
    -0.09
    ark
    -0.09
    otle
    -0.09
    ÑĥÑī
    -0.09
    resh
    -0.08
    iez
    -0.08
    èµ´
    -0.08
    peria
    -0.08
    _quality
    -0.08
    ness
    -0.08
    POSITIVE LOGITS
    åĨĮ
    0.12
    SED
    0.10
    åľºä¸Ĭ
    0.10
    ories
    0.10
    ivec
    0.09
    imonial
    0.09
    ä¸Ģä¸ĭ
    0.09
    ä¸İåıijå±ķ
    0.09
    ICLE
    0.09
    ç¼Ī
    0.08
    Activations Density 0.024%

    No Known Activations