© 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. 50338
    Prev
    Next
    INDEX
    Explanations

    ibooks / business

    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
    axy
    -0.09
    çŃ¹
    -0.09
    ya
    -0.09
    è¾ĸ
    -0.08
    ä¸į妨
    -0.08
     Nearly
    -0.08
    åĮ¿
    -0.08
    IRD
    -0.08
    ols
    -0.08
    ive
    -0.08
    POSITIVE LOGITS
    (Int
    0.12
    (In
    0.10
    ividual
    0.10
     /*<<<
    0.10
    ognito
    0.09
    è²ī
    0.09
    perial
    0.09
    ç»°
    0.09
    è¹´
    0.09
    abela
    0.09
    Activations Density 0.908%

    No Known Activations