© 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. 54866
    Prev
    Next
    INDEX
    Explanations

    dry wall, grain, distillation, state, weight

    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
    ally
    -0.11
    ennon
    -0.10
    ively
    -0.10
    ä¸Ģå®ļçļĦ
    -0.10
    ãĥ¼ãĥ³
    -0.10
    å¾Īæ¸ħæ¥ļ
    -0.09
    icher
    -0.09
    ially
    -0.09
    ions
    -0.09
     ìĿĺíķ´
    -0.08
    POSITIVE LOGITS
    holm
    0.11
    ãĥ¼ãĤº
    0.10
    å¾Ĺå¾Ī
    0.10
    wall
    0.09
    iculty
    0.09
    outube
    0.09
    sdale
    0.09
    bread
    0.09
    ers
    0.09
    ousse
    0.09
    Activations Density 0.011%

    No Known Activations