© 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. 48496
    Prev
    Next
    INDEX
    Explanations

    problems and complexities

    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
    ç»ıéªĮåĴĮ
    -0.10
    çĥŁçģ«
    -0.10
    管çIJĨåĴĮ
    -0.10
    ä¸Ģç¬ij
    -0.09
    _BS
    -0.09
    ÃŃf
    -0.08
    è´¨éĩıåĴĮ
    -0.08
    ç®ķ
    -0.08
    adam
    -0.08
    çĶŁäº§åĴĮ
    -0.08
    POSITIVE LOGITS
    åīįæīĢ
    0.12
    以èĩ³äºİ
    0.09
    åŁºåĩĨ
    0.09
    /or
    0.08
    ä½ľä¸ºä¸ĢåIJį
    0.08
    çĭ¸
    0.08
    ỡ
    0.08
     Petra
    0.08
    å°±å¦ĤåIJĮ
    0.08
    è°ĭ
    0.08
    Activations Density 0.245%

    No Known Activations