© 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. 34530
    Prev
    Next
    INDEX
    Explanations

    your [noun/website/resource]

    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
    伸
    -0.08
    第ä¸ī次
    -0.08
    åı¤
    -0.08
    Wis
    -0.07
    chin
    -0.07
    åIJĪ
    -0.07
    ÑĪиб
    -0.07
    ulp
    -0.07
    å¯Įæľī
    -0.07
    itur
    -0.07
    POSITIVE LOGITS
    еж
    0.11
    éĢļå¾Ģ
    0.10
    æķĽ
    0.10
    Friendly
    0.09
    ä»İæĿ¥ä¸į
    0.09
    лей
    0.09
    éĽĨèģļ
    0.09
    umed
    0.09
    棱
    0.09
    indow
    0.09
    Activations Density 0.029%

    No Known Activations