© 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. 996
    Prev
    Next
    INDEX
    Explanations

    copyright or authors

    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
    欲
    -0.08
    blem
    -0.08
    çĵĴ
    -0.08
    ather
    -0.08
    èĬ±èįī
    -0.08
    èĥ½ä½¿
    -0.08
    IRT
    -0.08
    ior
    -0.07
    iner
    -0.07
    ar
    -0.07
    POSITIVE LOGITS
    è°£
    0.10
    çĺŁ
    0.09
    à¹Ĥà¸Ī
    0.09
    _spi
    0.09
    à°Ĺ
    0.09
    _VC
    0.09
    ÑĤин
    0.09
    渺
    0.09
    -thumbnail
    0.08
    æľ¬çĿĢ
    0.08
    Activations Density 0.003%

    No Known Activations