© 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. 5771
    Prev
    Next
    INDEX
    Explanations

    cookie, biscuits

    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
    éĥ¯
    -0.10
    ãģĩ
    -0.10
    ively
    -0.09
    ä¸Ģ个æĺŁæľŁ
    -0.09
    rian
    -0.09
    iday
    -0.08
    ç¾İå¦Ļ
    -0.08
    _GRE
    -0.08
    _CB
    -0.08
    è¿ģ
    -0.08
    POSITIVE LOGITS
    _EVT
    0.10
    aceous
    0.09
    éĽ·è¾¾
    0.09
    åĽ½å®¶éĩįçĤ¹
    0.09
    !(:
    0.09
    аÑģÑĤ
    0.08
    æľīæĦıä¹ī
    0.08
    ä¸¥æł¼æī§è¡Į
    0.08
    asti
    0.08
    енÑĭ
    0.08
    Activations Density 0.004%

    No Known Activations