© 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. 62568
    Prev
    Next
    INDEX
    Explanations

    on / at

    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
    etine
    -0.10
    åIJĥå¾Ĺ
    -0.10
    èµ·æĿ¥äºĨ
    -0.09
    ç³Ł
    -0.09
    à°¡
    -0.09
    丼
    -0.09
    _delta
    -0.08
    æģį
    -0.08
    æķ¬è¯·
    -0.08
    æŀī
    -0.08
    POSITIVE LOGITS
    å·¡è§Ĩ
    0.09
    é«ĺèĢĥ
    0.09
     ass
    0.09
    è¡¥
    0.09
    ador
    0.08
    [token
    0.08
    ushima
    0.08
    åIJijãģį
    0.08
    gow
    0.08
    Reviews
    0.08
    Activations Density 0.065%

    No Known Activations