© 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. 32166
    Prev
    Next
    INDEX
    Explanations

    conditional conjunctions

    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
    .Future
    -0.09
    æįĨç»ij
    -0.09
    è´¹çİĩ
    -0.08
    ANDLE
    -0.08
    æĭ´
    -0.08
     Attribution
    -0.08
    BIT
    -0.08
    éĻĶ
    -0.08
    ä¸Ģç¬Ķ
    -0.07
    ç½²
    -0.07
    POSITIVE LOGITS
    ä¸ĭéĿ¢å°±
    0.11
    ä»Ĭ天æĪij们
    0.09
    æľ¬æĸĩ
    0.08
    ä¸ĭéĿ¢
    0.08
    广大å¸Ĥæ°ij
    0.08
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.08
     Reviewed
    0.08
    亲çĪ±
    0.08
    ä½łæĥ³
    0.08
    西å®īå¸Ĥ
    0.08
    Activations Density 0.761%

    No Known Activations