© 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. 34566
    Prev
    Next
    INDEX
    Explanations

    game mechanics and stats

    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
    ffen
    -0.09
    好åIJĹ
    -0.09
    EXTERN
    -0.09
    å®ıè§Ĥ
    -0.09
    æ±Ĭ
    -0.08
    erman
    -0.08
    ajs
    -0.08
    横åIJij
    -0.08
    夯å®ŀ
    -0.08
    _IL
    -0.08
    POSITIVE LOGITS
    å¿ĥæĥħ
    0.10
    çŃī级
    0.09
    åŁİå¸Ĥ建设
    0.09
    çĸ²åĬ³
    0.09
    èĮĦåŃIJ
    0.08
    èļ¯
    0.08
    Hur
    0.08
    æĥħ绪
    0.08
    engo
    0.08
    æijĦ
    0.08
    Activations Density 0.084%

    No Known Activations