© 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. 27845
    Prev
    Next
    INDEX
    Explanations

    multiplication and addition

    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
    æ¯ĶæĪij
    -0.09
    اث
    -0.09
    /people
    -0.09
    eld
    -0.08
    æį¢æĪIJ
    -0.07
    çŀ¥
    -0.07
    اÙĤÙĦ
    -0.07
    æĸ°åĬł
    -0.07
    å¡«æĬ¥
    -0.07
     Brendan
    -0.07
    POSITIVE LOGITS
    ahan
    0.09
    å½ĵçĦ¶
    0.09
    ä¼IJ
    0.09
    éĿ
    0.09
    íĥĪ
    0.09
    rido
    0.09
    _simps
    0.09
    éªĬ
    0.09
    ฤ
    0.08
    إص
    0.08
    Activations Density 0.272%

    No Known Activations