© 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. 62018
    Prev
    Next
    INDEX
    Explanations

    From the

    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
    éĻħ
    -0.11
    opus
    -0.08
    èĢģ头
    -0.08
    ê¶Į
    -0.08
     Clair
    -0.08
    umpy
    -0.08
    å¸ĥæľĹ
    -0.08
    ÑĤай
    -0.08
    yen
    -0.08
    icap
    -0.08
    POSITIVE LOGITS
    å¥Ī
    0.10
    åIJįæł¡
    0.10
    åı¯ä»¥çľĭåĩº
    0.10
    æī§æķĻ
    0.09
     standpoint
    0.09
    ä¸įä¿¡
    0.09
    èĥ½çľĭåĩº
    0.09
     perspective
    0.09
    cribing
    0.09
    ä¼ı
    0.09
    Activations Density 0.051%

    No Known Activations