© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53013
    Prev
    Next
    INDEX
    Explanations

    mozilla.org

    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
    åħļå§Ķ
    -0.09
    sted
    -0.08
    essa
    -0.08
    ç¼´
    -0.08
    åĬ¡
    -0.08
    ement
    -0.08
    Jet
    -0.08
     Brew
    -0.08
    bw
    -0.07
    uzzi
    -0.07
    POSITIVE LOGITS
    ä¼Ĭæĸ¯
    0.09
    åĬłå¿«å»ºè®¾
    0.09
    æĻĹ
    0.09
    æĿ¾å¼Ľ
    0.09
    enting
    0.09
    _CLIP
    0.09
    湿度
    0.08
     Lumia
    0.08
    rib
    0.08
    è¨Ģè¡Į
    0.08
    Activations Density 0.001%

    No Known Activations