© 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. 35148
    Prev
    Next
    INDEX
    Explanations

    ask questions

    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
    çŃĶå¤į
    -0.09
    atsu
    -0.08
     pant
    -0.08
    tera
    -0.08
    èĽĭ
    -0.08
    _reply
    -0.08
    ç´ł
    -0.08
    å¿ĥ头
    -0.08
    å·¢
    -0.08
    æīĴ
    -0.08
    POSITIVE LOGITS
    åĪ«äºº
    0.10
    apas
    0.09
     Harrison
    0.09
    ç»Ī
    0.09
    los
    0.08
    Ticker
    0.08
    details
    0.08
     Brandon
    0.08
    è
    0.08
    ç½ķ
    0.08
    Activations Density 0.158%

    No Known Activations