© 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. 31874
    Prev
    Next
    INDEX
    Explanations

    Vim and Bram

    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
    å¥Ķ
    -0.10
    æijĩ
    -0.09
     Prim
    -0.09
    Prim
    -0.09
    éĻ¤
    -0.09
    æµģæ°ĵ
    -0.09
    å¥ī
    -0.09
    cn
    -0.08
    çĽĹ
    -0.08
    æ²ĥ
    -0.08
    POSITIVE LOGITS
    èĸ¤
    0.10
    æ¥Ķ
    0.10
     Willie
    0.09
     SOUR
    0.09
    iced
    0.09
    é±
    0.09
     Vim
    0.09
    é³Ĭ
    0.09
    æĻļ
    0.08
     Lair
    0.08
    Activations Density 0.174%

    No Known Activations