© 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. 39348
    Prev
    Next
    INDEX
    Explanations

    primary sources

    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
    æľ¦
    -0.09
     Lund
    -0.09
    ipple
    -0.09
    éģĹå¿ĺ
    -0.09
    éŵ
    -0.09
    è¿Ł
    -0.09
    ushi
    -0.09
    lement
    -0.09
    æĩµ
    -0.09
    髦
    -0.09
    POSITIVE LOGITS
     sources
    0.11
    éĢĤåIJĪèĩªå·±
    0.11
    icana
    0.10
    éĵł
    0.10
    æĶ¶éĽĨ
    0.09
    sources
    0.09
    æIJľéĽĨ
    0.09
    æĿĥå¨ģ
    0.09
    åı¯éĿł
    0.09
    槽
    0.09
    Activations Density 0.035%

    No Known Activations