© 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. 33685
    Prev
    Next
    INDEX
    Explanations

    requirement or obligation

    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
    гÑĢÑĥз
    -0.09
    æĹĹ
    -0.09
    ги
    -0.09
     Seas
    -0.08
    sville
    -0.08
    çľº
    -0.08
    ä¸į解
    -0.08
     provisional
    -0.08
    ä¸įåIJĪ
    -0.08
    rote
    -0.08
    POSITIVE LOGITS
    è¿ĺè¦ģ
    0.17
    éĤĦè¦ģ
    0.15
    è¿ĺéľĢè¦ģ
    0.14
    è¿ĺå¾Ĺ
    0.14
    è¿ĺæľīå¾Īå¤ļ
    0.13
    è¿ĺæľīä¸ĢäºĽ
    0.12
    è¿ĺéľĢ
    0.12
    éĤĦæľī
    0.11
    è¿ĺæľī
    0.11
    æīįç®Ĺ
    0.11
    Activations Density 0.083%

    No Known Activations