© 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. 6784
    Prev
    Next
    INDEX
    Explanations

    debt solution to

    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
    umo
    -0.10
    isible
    -0.09
    apos
    -0.08
    [port
    -0.08
    <th
    -0.08
     hÆ°á»Łng
    -0.08
    æ¸ĹéĢı
    -0.08
    LinkId
    -0.08
    à¸ķะ
    -0.08
    _WRAP
    -0.08
    POSITIVE LOGITS
    éķĩåħļå§Ķ
    0.10
    å¾Īå¤ļæľĭåıĭ
    0.10
    æĪij个人
    0.10
    åħ¨ä½ĵåijĺå·¥
    0.10
    æĹłè¾ľ
    0.09
    åĥŃ
    0.09
    ä¸Ńåįİæ°ijæĹı
    0.09
    å·¥ä½ľæĸ¹æ¡Ī
    0.09
    ç»Ļä½łä»¬
    0.09
    常åĬ¡åī¯
    0.09
    Activations Density 0.133%

    No Known Activations