© 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. 63622
    Prev
    Next
    INDEX
    Explanations

    form or momentum

    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
    åĵī
    -0.09
    ä¸Ģ头
    -0.09
    åĿĿ
    -0.09
    è°Ĵ
    -0.08
    ://
    -0.08
    è¿Ľåľº
    -0.08
    åľ¨ä¹İ
    -0.08
    å®ĮäºĨ
    -0.08
    еÑĩ
    -0.08
    çĿĢæĢ¥
    -0.08
    POSITIVE LOGITS
    å¾®åįļ
    0.09
    ulen
    0.08
    essaging
    0.08
    åīįèĢħ
    0.08
    _disp
    0.08
    artment
    0.08
    Disp
    0.08
    è¾¾ä¸įåĪ°
    0.08
    èĭ
    0.08
    çĶŁäº§åĬĽ
    0.08
    Activations Density 0.022%

    No Known Activations