© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20051
    Prev
    Next
    INDEX
    Explanations

    under one or more

    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
    端æŃ£
    -0.09
    èķĬ
    -0.09
    åľ¨éĩĮéĿ¢
    -0.09
    èĩ³æѤ
    -0.08
    åľ¨æѤ
    -0.08
    åľ¨æĦı
    -0.08
    è¸ı
    -0.08
     dressing
    -0.08
    trl
    -0.08
    å´ĸ
    -0.08
    POSITIVE LOGITS
     guise
    0.15
     ausp
    0.12
     circumstances
    0.10
     headings
    0.10
    æ¢Ŀ
    0.10
    neath
    0.10
     conditions
    0.09
     heading
    0.09
    åıijå¸ĥæŶéĹ´
    0.09
    åħ¬åı¸ç«łç¨ĭ
    0.09
    Activations Density 0.207%

    No Known Activations