© 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. 51824
    Prev
    Next
    INDEX
    Explanations

    bingo and slot games

    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
    arya
    -0.11
    inox
    -0.09
    åľ¨æ¸¸æĪıä¸Ń
    -0.09
    íģ¼
    -0.09
    <![
    -0.09
    åħ±åĪĽ
    -0.09
    åłij
    -0.09
     Intl
    -0.08
    prt
    -0.08
    ä¸ĵ访
    -0.08
    POSITIVE LOGITS
    iska
    0.09
    楣
    0.09
    laus
    0.08
    forc
    0.08
    Cog
    0.08
    IFY
    0.08
    è¡£
    0.08
    è¹ĭ
    0.08
    ees
    0.08
    oola
    0.08
    Activations Density 0.008%

    No Known Activations