© 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. 20065
    Prev
    Next
    INDEX
    Explanations

    use / using

    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
    æ´ĭæ´ĭ
    -0.10
    举
    -0.09
    fern
    -0.09
    åĨ·åĨ·
    -0.08
    æĥħ人
    -0.08
    é©¿
    -0.08
    SELF
    -0.08
    ERVER
    -0.08
    çļĩåĨł
    -0.08
    sect
    -0.08
    POSITIVE LOGITS
    è¿ĩçļĦ
    0.10
    å½ĵåľ°äºº
    0.10
    å·²ä¹ħ
    0.09
    åĽ½äº§
    0.09
    ilian
    0.09
    åįļçī©
    0.08
    ä¹ĭ乡
    0.08
     давно
    0.08
     dür
    0.08
    çªŃ
    0.08
    Activations Density 0.397%

    No Known Activations