© 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. 10673
    Prev
    Next
    INDEX
    Explanations

    as such

    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
    oure
    -0.09
     bức
    -0.09
    iven
    -0.09
    _FIFO
    -0.09
    dif
    -0.09
    ipi
    -0.08
    åIJ¸
    -0.08
    è°İè¨Ģ
    -0.08
    IVEN
    -0.08
    åݦ
    -0.08
    POSITIVE LOGITS
     Manit
    0.09
    OOK
    0.09
     zro
    0.09
    æľ¬ç½ij
    0.09
    æ´
    0.08
    intage
    0.08
    å¨
    0.08
    imer
    0.08
    并æĹł
    0.08
    æĢ
    0.08
    Activations Density 0.016%

    No Known Activations