© 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. 3529
    Prev
    Next
    INDEX
    Explanations

    words

    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
    icie
    -0.09
    åħ±åĴĮ
    -0.08
    otion
    -0.08
    secs
    -0.08
    ุม
    -0.08
    åįķä¸Ģ
    -0.08
    èľ¡
    -0.08
    èĽİ
    -0.08
    asis
    -0.08
    istory
    -0.08
    POSITIVE LOGITS
    mith
    0.13
     Words
    0.11
    WORDS
    0.11
    (words
    0.11
    é¦ĸåıij
    0.11
    è¯ł
    0.11
    .words
    0.11
     words
    0.11
     Ñģловам
    0.10
    words
    0.10
    Activations Density 0.107%

    No Known Activations