© 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. 20373
    Prev
    Next
    INDEX
    Explanations

    to [verb]

    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
    oted
    -0.10
    å¨ĥå¨ĥ
    -0.10
    kle
    -0.09
    åŁ¤
    -0.09
    çĻ½è¡£
    -0.09
    åĩºå¢ĥ
    -0.08
    èĽŁ
    -0.08
    ãĥįãĤ¿
    -0.08
    ned
    -0.08
    çºł
    -0.08
    POSITIVE LOGITS
    æĪĺäºī
    0.11
    plen
    0.09
    pps
    0.09
    ancock
    0.09
    éī´
    0.08
    erto
    0.08
    æĪIJ为ä¸Ģ个
    0.08
    ê¹ĥ
    0.08
    izontal
    0.08
    座
    0.08
    Activations Density 0.055%

    No Known Activations