© 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. 61216
    Prev
    Next
    INDEX
    Explanations

    equal number, groups, probability, amounts, size, or measure

    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
    mere
    -0.09
    ç»Ī
    -0.09
    奢ä¾Ī
    -0.09
    顺便
    -0.08
    berry
    -0.08
    ä¹ĭæīĢ以
    -0.08
    CommandEvent
    -0.08
    äºĭå®ľ
    -0.08
    _EXTRA
    -0.08
    主æĦı
    -0.08
    POSITIVE LOGITS
     equally
    0.14
    (equal
    0.12
    Equal
    0.12
     equal
    0.12
    EQUAL
    0.12
    éķ¿çŁŃ
    0.12
    (Equal
    0.12
    åIJĮçŃī
    0.12
    å¹³çŃī
    0.11
    åħ¬å¹³
    0.11
    Activations Density 0.087%

    No Known Activations