© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9820
    Prev
    Next
    INDEX
    Explanations

    sports team names

    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
    å¾Ĵ
    -0.11
    ror
    -0.09
    ç§ijæĬĢè¿ĽæŃ¥
    -0.09
    追
    -0.09
    åģļä¸Ģ个
    -0.09
    rant
    -0.08
    noop
    -0.08
    pla
    -0.08
    omer
    -0.08
    ç¿ķ
    -0.08
    POSITIVE LOGITS
    stry
    0.10
    åķ
    0.10
    ful
    0.09
    yat
    0.09
    ä¸ĢæĬĬ
    0.09
    ematic
    0.09
    èĻ¬
    0.08
    人士
    0.08
    unge
    0.08
    çī¢åĽº
    0.08
    Activations Density 0.007%

    No Known Activations