© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37285
    Prev
    Next
    INDEX
    Explanations

    copyright and time stamps

    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
    æ²IJæµ´
    -0.10
    quee
    -0.10
    æĹłå£°
    -0.09
    jee
    -0.09
    磼
    -0.09
    åŃ£
    -0.09
    åıįæĺł
    -0.09
    æµ´
    -0.09
    åı¸æ³ķ
    -0.09
    人éĹ´
    -0.09
    POSITIVE LOGITS
    æŃī
    0.09
    ancell
    0.09
    èĮĢ
    0.08
    èĥĻ
    0.08
    icol
    0.08
    æ¸ħè¿ľ
    0.08
    ä¸Ģæľ¬
    0.08
    æ£ł
    0.08
    è±Ĩçĵ£
    0.08
    Pub
    0.08
    Activations Density 0.031%

    No Known Activations