© 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. 35357
    Prev
    Next
    INDEX
    Explanations

    Ribbon, Gloves, belt

    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
    æľ¬ç½ij
    -0.14
    _MASTER
    -0.09
    å«Ķ
    -0.09
    çļĦåij³éģĵ
    -0.08
    èµı
    -0.08
    æĢ§åĴĮ
    -0.08
     bú
    -0.08
    æ°Ķæģ¯
    -0.08
     compar
    -0.08
    rias
    -0.08
    POSITIVE LOGITS
    å·¾
    0.10
    çģ°èī²
    0.09
    ulet
    0.09
    anke
    0.09
    Sad
    0.09
    oran
    0.09
    ï¸
    0.08
    è¢ĸ
    0.08
    anca
    0.08
    agenta
    0.08
    Activations Density 0.094%

    No Known Activations