© 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. 1878
    Prev
    Next
    INDEX
    Explanations

    you're either/or

    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
    å°ıäºĭ
    -0.11
    å§Ĭ妹
    -0.10
    nyder
    -0.09
    大æłij
    -0.09
    æºĥ
    -0.09
     Layers
    -0.09
    æĪij们认为
    -0.08
    稼
    -0.08
    åıªè¦ģä½ł
    -0.08
    ä¸įçIJĨ
    -0.08
    POSITIVE LOGITS
    åĽ¿
    0.10
     own
    0.09
     lucky
    0.09
     excessive
    0.09
    pur
    0.08
    tol
    0.08
     Chr
    0.08
    aspberry
    0.08
    ç´łè´¨
    0.08
    efined
    0.08
    Activations Density 0.024%

    No Known Activations