© 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. 52736
    Prev
    Next
    INDEX
    Explanations

    calling for

    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
     кажеÑĤÑģÑı
    -0.09
    ä¿İ
    -0.09
    elin
    -0.09
    omm
    -0.08
    uv
    -0.08
    çĺł
    -0.08
    èĢĥåľº
    -0.08
    å°±æĦıåij³çĿĢ
    -0.08
    å®ŀéĻħæĥħåĨµ
    -0.08
    æİ¥è¿ĩ
    -0.08
    POSITIVE LOGITS
    æīĢæľī人éĥ½
    0.10
    oused
    0.09
    ither
    0.09
    uset
    0.09
    izin
    0.08
    ìŀ¥ìĿĦ
    0.08
    å©Ĩ
    0.08
    ibrator
    0.08
    çļĦæĺ¯
    0.08
    ä¹ĭ声
    0.08
    Activations Density 0.012%

    No Known Activations