© 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. 38023
    Prev
    Next
    INDEX
    Explanations

    then enter

    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
    çļĭ
    -0.09
    pto
    -0.08
    å¹
    -0.08
    itol
    -0.08
    isible
    -0.08
    ptom
    -0.08
    AMES
    -0.08
    建档
    -0.08
    æĮĤéĴ©
    -0.08
    åĪŃ
    -0.08
    POSITIVE LOGITS
    ä¿©
    0.09
    èģĮ
    0.09
    å¨ĺ
    0.09
    HITE
    0.09
    (acc
    0.09
    身边
    0.09
    åģļ大
    0.08
    身ä¸Ĭ
    0.08
    大éŨ
    0.08
    elves
    0.08
    Activations Density 0.115%

    No Known Activations