© 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. 3334
    Prev
    Next
    INDEX
    Explanations

    have followed by a noun/pronoun

    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
    è¦ģæĬĬ
    -0.12
    OrNull
    -0.09
    å·¥ä½ľä½ľé£İ
    -0.09
    该æĢİä¹Ī
    -0.09
    rent
    -0.09
    ãģĦãģĭ
    -0.09
     Chatt
    -0.09
    èĭ¥å¹²
    -0.09
    åı¯ä»¥ä½¿
    -0.09
    ä½
    -0.09
    POSITIVE LOGITS
    OrUpdate
    0.10
     lam
    0.08
    Щ
    0.08
     Fair
    0.08
    è¿ĻåĿĹ
    0.08
    /control
    0.08
    ä¸Ģçĵ¶
    0.08
    ably
    0.08
    羣æŃ£çļĦ
    0.08
    æĽ³
    0.08
    Activations Density 0.028%

    No Known Activations