© 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. 51424
    Prev
    Next
    INDEX
    Explanations

    that something

    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
    ä¹Łå¥½
    -0.11
    ä¼Ĭæĭī
    -0.11
    èĻ
    -0.10
    æĢĿè·¯
    -0.09
    æīĢ以æĪij们
    -0.09
    izzle
    -0.09
    ä¹Łå°±
    -0.09
    tutorial
    -0.09
    æĬĬæĪij
    -0.08
    otti
    -0.08
    POSITIVE LOGITS
    _BLE
    0.09
    è¿ĺä¸įæĺ¯
    0.09
    uja
    0.09
    éĤ£æŶ
    0.09
    è®Ń
    0.08
    ripple
    0.08
    çł´
    0.08
    ä¸įä¸Ģå®ļ
    0.08
     streak
    0.08
    èī¯
    0.08
    Activations Density 0.029%

    No Known Activations