© 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. 7530
    Prev
    Next
    INDEX
    Explanations

    megakilopeta frequency and size

    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
    ÑĪе
    -0.10
    èµ°å»Ĭ
    -0.09
    é¢ļ
    -0.09
    isContained
    -0.08
    颤æĬĸ
    -0.08
    imat
    -0.08
    èĽŃ
    -0.08
    ãĤ¢ãĤ¦
    -0.08
     ÙĪجÙĩ
    -0.08
    é¬ĵ
    -0.08
    POSITIVE LOGITS
    çĤ¯
    0.09
    éªĩ
    0.09
    æīĵéĢłæĪIJ
    0.09
    å®Įç»ĵ
    0.09
    burgh
    0.08
    ELS
    0.08
    åĬĽãĤĴ
    0.08
    æĸĩåĮĸ交æµģ
    0.08
    á»±c
    0.08
    æĨ§æĨ¬
    0.08
    Activations Density 0.071%

    No Known Activations