© 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. 7292
    Prev
    Next
    INDEX
    Explanations

    may followed by verbs

    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
    UNC
    -0.09
     extrem
    -0.08
    头ä¸Ĭ
    -0.08
    åĽĽæĸ¹
    -0.08
    ble
    -0.08
    é«ĺåľ°
    -0.08
     mural
    -0.08
    ÑĤиÑĢ
    -0.08
    çľī
    -0.08
    edBy
    -0.07
    POSITIVE LOGITS
    ä¸Ģ天
    0.09
    éĹªçĥģ
    0.09
    æī³
    0.09
    æĸĩæ¡Ī
    0.09
    åĬŃ
    0.09
    éħ¬
    0.08
    веÑĢÑħ
    0.08
    Sizes
    0.08
     otherwise
    0.08
    coles
    0.08
    Activations Density 0.080%

    No Known Activations