© 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. 54542
    Prev
    Next
    INDEX
    Explanations

    holidays

    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
    缨
    -0.09
    èĦ
    -0.09
     comb
    -0.09
    ä¸Ģç§į
    -0.08
    å¥ī
    -0.08
    缩å°ı
    -0.08
    ounter
    -0.08
    /pkg
    -0.08
    æľī两ç§į
    -0.08
    羣缸
    -0.08
    POSITIVE LOGITS
    ä¸įå¿į
    0.09
    åŁºæķ°
    0.08
    æ¶ĪèĢĹ
    0.08
    :void
    0.08
    åīįä¸ī
    0.08
     Bend
    0.08
    èľ©
    0.08
    crate
    0.08
    away
    0.08
    èĩªçĦ¶
    0.08
    Activations Density 0.031%

    No Known Activations