© 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. 56768
    Prev
    Next
    INDEX
    Explanations

    clipped, muted, organic sounds

    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
    ä¸Ģå¤ľ
    -0.11
    ä¸Ģç«Ļ
    -0.10
     ÑģовеÑĢÑĪен
    -0.09
     давно
    -0.09
    SGlobal
    -0.09
    å¿ĥä¸ŃçļĦ
    -0.09
    ç¹ģå¿Ļ
    -0.09
    ictions
    -0.09
    大家éĥ½åľ¨
    -0.09
    åĬ¬
    -0.09
    POSITIVE LOGITS
    强çĥĪ
    0.10
    å¼ıçļĦ
    0.09
    è·³è·ĥ
    0.08
    .getB
    0.08
    wis
    0.08
    è±¹
    0.08
     полÑĥ
    0.08
    çĮİ
    0.07
    setId
    0.07
    emple
    0.07
    Activations Density 0.033%

    No Known Activations