© 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. 1676
    Prev
    Next
    INDEX
    Explanations

    grant permission

    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
    æĥħåĨµè¿Ľè¡Į
    -0.10
    æ¶Īè´¹åįĩ级
    -0.09
    èĸĦå¼±
    -0.09
    çĤ¹å¤ļ
    -0.09
    秦
    -0.09
    å¼ŁåħĦ
    -0.08
    azz
    -0.08
    ä¸Ģ个èģĮä¸ļ
    -0.08
    ä¸Ģéģį
    -0.08
     Gam
    -0.08
    POSITIVE LOGITS
    å¿ĥ缮ä¸Ń
    0.09
    è°´
    0.09
     Metro
    0.08
    å®Ī
    0.08
    为é¦ĸ
    0.08
     metro
    0.08
    ousand
    0.08
    CONTEXT
    0.08
    BH
    0.08
    ç¥ĸåĽ½
    0.08
    Activations Density 0.015%

    No Known Activations