© 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. 34908
    Prev
    Next
    INDEX
    Explanations

    verbs describing states or actions

    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
    åįĹè·¯
    -0.10
     wÅĽ
    -0.10
    éĹ®ä¸ĸ
    -0.09
    åħ¨æĹ¥
    -0.09
    诡
    -0.09
     spo
    -0.09
    åİŁä»¶
    -0.09
    dorf
    -0.09
    åı¤æĢª
    -0.09
    çİ¥
    -0.09
    POSITIVE LOGITS
    ied
    0.10
     Rush
    0.07
    ij
    0.07
    undef
    0.07
    agements
    0.07
     Lind
    0.07
    ies
    0.07
     Mans
    0.07
     b
    0.07
    raft
    0.07
    Activations Density 1.012%

    No Known Activations