© 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. 33512
    Prev
    Next
    INDEX
    Explanations

    role or requirements or demand

    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
    æĢİä¹ĪåĽŀäºĭ
    -0.08
    客æĪ·æıIJä¾Ľ
    -0.08
    大声
    -0.08
    ç«Ń
    -0.08
    éī´
    -0.08
    /of
    -0.08
    ÅĽmy
    -0.07
    ä¼ģä¸ļæıIJä¾Ľ
    -0.07
    为代表çļĦ
    -0.07
    åĽŀäºĭ
    -0.07
    POSITIVE LOGITS
    å¾Ģå¾Ģæĺ¯
    0.10
    å®ŀåľ¨å¤ª
    0.10
    马ä¸Ĭå°±
    0.10
    ä¹ŁåĽłæѤ
    0.10
    åį´æĺ¯
    0.10
    åį´
    0.09
    ertz
    0.09
    éĢļ常æĺ¯
    0.09
    indow
    0.09
    羣çļĦå¾Ī
    0.09
    Activations Density 0.425%

    No Known Activations