© 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. 55109
    Prev
    Next
    INDEX
    Explanations

    copyright, http, font, and license information

    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
    éĤ£ä¹Īå¤ļ
    -0.11
    lessly
    -0.09
    éŁŃèıľ
    -0.09
    æĦŁæĥħ
    -0.09
    åı¯è°ĵ
    -0.08
    æ°Ķæģ¯
    -0.08
    åİĨå¹´
    -0.08
    èŁ
    -0.08
    PTR
    -0.08
    ãģĵãģĿ
    -0.08
    POSITIVE LOGITS
    æ·±æ¸Ĭ
    0.10
    èĪ
    0.10
     понÑĢав
    0.09
     unn
    0.09
    mps
    0.09
     Wrest
    0.09
    èĪį
    0.09
    å·¦æīĭ
    0.09
    为å¥ijæľº
    0.09
     styl
    0.09
    Activations Density 0.593%

    No Known Activations