© 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. 49807
    Prev
    Next
    INDEX
    Explanations

    treaty or pact ratified

    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
    uard
    -0.09
    nil
    -0.09
    æ©¡
    -0.09
    _syntax
    -0.09
    å§Ĭ
    -0.09
    çģµæķı
    -0.09
    atem
    -0.09
    åĨľä½ľçī©
    -0.09
    -nil
    -0.09
    æīĴ
    -0.09
    POSITIVE LOGITS
    æĿ¡çº¦
    0.14
     treaty
    0.12
    åįıå®ļ
    0.11
    è°ĪåĪ¤
    0.11
     Treaty
    0.10
    éļĨ
    0.09
     pact
    0.09
    rico
    0.09
    å¤ĸ交
    0.09
    æį¢æĿ¥
    0.08
    Activations Density 0.076%

    No Known Activations