© 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. 28019
    Prev
    Next
    INDEX
    Explanations

    libraries: libuno_sal.so.3.shared libraries

    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
    wash
    -0.10
    èļĢ
    -0.09
    ä¸įä¿¡
    -0.09
    attles
    -0.09
    agra
    -0.08
    åī½
    -0.08
    ç½®
    -0.08
    criptor
    -0.08
    Trump
    -0.08
    æ·±åľ³å¸Ĥ
    -0.08
    POSITIVE LOGITS
    èĦ¸éĥ¨
    0.10
    çľĭä¸Ģçľĭ
    0.09
    headed
    0.09
    åİĨ代
    0.09
    çĭĤ
    0.09
    WithType
    0.09
    ndx
    0.08
    éĩįåŀĭ
    0.08
    iba
    0.08
    ä¸įè§ģ
    0.08
    Activations Density 0.138%

    No Known Activations