© 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. 27476
    Prev
    Next
    INDEX
    Explanations

    flair or style

    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
    apia
    -0.09
    oce
    -0.09
    cy
    -0.09
    许å¤ļ
    -0.08
    па
    -0.08
    åį´ä¸į
    -0.08
    hips
    -0.08
     Logged
    -0.08
    äºĨ好å¤ļ
    -0.08
    lik
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.17
    0.12
     quo
    0.09
    è¿Ń
    0.09
    åĭĥåĭĥ
    0.08
    æīĢåľ¨
    0.08
    åijĽ
    0.08
    iest
    0.08
    ocratic
    0.08
    getter
    0.08
    Activations Density 0.014%

    No Known Activations