© 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. 34712
    Prev
    Next
    INDEX
    Explanations

    functional programming

    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
    arsed
    -0.10
    沿çĿĢ
    -0.09
    å®Įæķ´çļĦ
    -0.09
    è¹Ī
    -0.09
    å¯Ŀ
    -0.09
    å¸ĮæľĽèĩªå·±
    -0.09
    .pkg
    -0.09
    inas
    -0.08
    fft
    -0.08
    arend
    -0.08
    POSITIVE LOGITS
     jer
    0.09
    å«ģ
    0.08
    åĮ¿åIJį
    0.08
    (callback
    0.08
     Musk
    0.08
    æ·¡åĮĸ
    0.08
    åĻ©
    0.08
    æł¸å®ļ
    0.08
    罩
    0.08
    9
    0.08
    Activations Density 0.531%

    No Known Activations