© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36320
    Prev
    Next
    INDEX
    Explanations

    filling containers with liquid

    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
    女ç¥ŀ
    -0.10
    天çĶŁ
    -0.10
    ä¸ĢæĿ¯
    -0.09
    _bag
    -0.09
    .Typed
    -0.09
     оÑĤзÑĭв
    -0.09
    URY
    -0.08
    pagen
    -0.08
    çĥŁåĽ±
    -0.08
    åľ¨æĦı
    -0.08
    POSITIVE LOGITS
    æļ´
    0.10
    arrera
    0.09
     Transcript
    0.09
    reek
    0.09
    è¶Ĭå¤ļ
    0.08
    Returned
    0.08
    çªĥ
    0.08
    lectron
    0.08
    å¤ĩ
    0.08
    èİ·å¾ĹæĽ´å¤ļ
    0.08
    Activations Density 0.056%

    No Known Activations