© 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. 29998
    Prev
    Next
    INDEX
    Explanations

    credit: names and sources

    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
    ParameterValue
    -0.09
    ä¿Ĺ
    -0.09
    ICI
    -0.09
    .cz
    -0.08
    .CV
    -0.08
    /rfc
    -0.08
    æıIJçİ°
    -0.08
    olated
    -0.08
    æĸ°çļĦä¸Ģå¹´
    -0.08
     interception
    -0.08
    POSITIVE LOGITS
    ä½ľèĢħæľ¬äºº
    0.11
    第ä¸īèĢħ
    0.09
    thew
    0.09
    mos
    0.08
    uckle
    0.08
    æĸ½
    0.08
    ä»Ģä¹ĪåİŁåĽł
    0.08
    æĿİåħĪçĶŁ
    0.08
    æĪijèĩªå·±
    0.08
    ESS
    0.08
    Activations Density 0.009%

    No Known Activations