© 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. 2373
    Prev
    Next
    INDEX
    Explanations

    results and interpretation

    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
    çģ«è½¦
    -0.09
    çģµæĦŁ
    -0.09
    çĥŃæ°´
    -0.09
     sensors
    -0.09
    ä¼łæĦŁåĻ¨
    -0.09
    ç¥Ŀ
    -0.09
    è¬Ĥ
    -0.08
     Picker
    -0.08
    eil
    -0.08
    flash
    -0.08
    POSITIVE LOGITS
    ç»ĵæŀľ
    0.18
     results
    0.15
    çµIJæŀľ
    0.15
     Results
    0.14
    results
    0.14
    ç»ĵ论
    0.14
    .results
    0.13
    Results
    0.13
    _RESULTS
    0.13
    _results
    0.13
    Activations Density 0.265%

    No Known Activations