© 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. 23908
    Prev
    Next
    INDEX
    Explanations

    near a or 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
    æĭĶ
    -0.09
    åİŁåĪĻä¸Ĭ
    -0.09
    åıįåºĶ
    -0.08
    amu
    -0.08
    ç©
    -0.08
     Erl
    -0.08
    èĹī
    -0.08
    éĢĨè¡Į
    -0.08
    ä¸ĢèĪ¬æĿ¥è¯´
    -0.08
    ç±į
    -0.07
    POSITIVE LOGITS
     à¹Ĩ
    0.12
    交éĢļæŀ¢çº½
    0.11
     водо
    0.11
    å¹´åºķ
    0.10
    æ°´æºIJ
    0.10
    /at
    0.10
    ãĤ¹ãĥĶ
    0.10
    åºķéĥ¨
    0.10
    isans
    0.10
    åĪĿå¿ĥ
    0.10
    Activations Density 0.060%

    No Known Activations