© 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. 49251
    Prev
    Next
    INDEX
    Explanations

    more recent

    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
    è·¯çģ¯
    -0.11
    éĶij
    -0.10
    locals
    -0.10
    idia
    -0.09
     lamp
    -0.09
    åĿļå®ļä¸į移
    -0.09
    leness
    -0.09
    åĨľæľº
    -0.09
    xcb
    -0.09
     пеÑĩ
    -0.09
    POSITIVE LOGITS
    ä¿¡æģ¯åĮĸ
    0.11
    åħ¨çIJĥåĮĸ
    0.10
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.10
     modern
    0.10
    è¶ĬæĿ¥è¶Ĭ
    0.09
    å¤ļåħĥåĮĸ
    0.09
    ruz
    0.09
    çݰ代
    0.09
    äºĴèģĶç½ij
    0.09
    ä¸įåĨįæĺ¯
    0.09
    Activations Density 0.594%

    No Known Activations