© 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. 26962
    Prev
    Next
    INDEX
    Explanations

    bass strings or player

    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
    ations
    -0.11
    pee
    -0.09
    ä»Ģä¹Īæł·
    -0.09
    pty
    -0.09
    reso
    -0.09
    诰
    -0.09
    ../
    -0.09
    ation
    -0.09
    orate
    -0.08
    æľįåĬ¡æ°´å¹³
    -0.08
    POSITIVE LOGITS
    ะ
    0.12
    ðŁı»
    0.12
    curity
    0.09
    ãĤ§
    0.09
    ика
    0.09
    丸
    0.09
    aign
    0.09
    oon
    0.08
    chool
    0.08
    erman
    0.08
    Activations Density 0.008%

    No Known Activations