© 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. 30928
    Prev
    Next
    INDEX
    Explanations

    specific items

    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
    erman
    -0.10
    åıijçİ°èĩªå·±
    -0.10
    ìĦľ
    -0.10
    èīºäºº
    -0.09
    ãĤ£
    -0.09
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.09
    intosh
    -0.09
    ðŁı»
    -0.09
    lan
    -0.09
    lor
    -0.09
    POSITIVE LOGITS
    perature
    0.12
    ized
    0.11
    /people
    0.10
    à¹Ĥà¸Ľà¸£à¸Ķ
    0.10
    bez
    0.09
    Gtk
    0.09
    è²Ĥ
    0.09
    getter
    0.09
    诸å¦Ĥ
    0.09
    .SubItems
    0.09
    Activations Density 0.044%

    No Known Activations