© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37367
    Prev
    Next
    INDEX
    Explanations

    log in or username

    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
    .va
    -0.08
    ç°Ł
    -0.08
    mour
    -0.08
    åī¡
    -0.08
     Jed
    -0.08
    çīĴ
    -0.07
    æ··åĩĿåľŁ
    -0.07
     pred
    -0.07
    æºľ
    -0.07
    atta
    -0.07
    POSITIVE LOGITS
    åĴĮåıijå±ķ
    0.12
    OrCreate
    0.09
    éĹ¨æ§Ľ
    0.09
    ãĥĥãĤ·
    0.09
    icians
    0.09
    gings
    0.09
    gear
    0.09
    ulu
    0.09
    é¹Ĺ
    0.09
    æĦ¿æľĽ
    0.09
    Activations Density 0.020%

    No Known Activations