© 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. 61689
    Prev
    Next
    INDEX
    Explanations

    exit code or status

    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
     ata
    -0.09
    槽
    -0.08
     pert
    -0.08
    èģĶåIJĪ
    -0.08
    frag
    -0.08
    ç»ĦæĪIJéĥ¨åĪĨ
    -0.07
    íħIJ
    -0.07
     frag
    -0.07
    _ENDIAN
    -0.07
    imin
    -0.07
    POSITIVE LOGITS
    è¿ĶåĽŀ
    0.14
     è¿ĶåĽŀ
    0.12
    alse
    0.11
     Return
    0.11
    Return
    0.11
    åĽŀæĿ¥
    0.10
     returned
    0.10
    åĽŀåĪ°
    0.10
     $?
    0.10
    æĦıå¤ĸ
    0.10
    Activations Density 0.483%

    No Known Activations