© 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. 55829
    Prev
    Next
    INDEX
    Explanations

    as X as Y, like X

    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
    AGAIN
    -0.09
    åı¯æĢľ
    -0.08
    ASA
    -0.08
    使æĪij
    -0.08
    常德
    -0.08
    _tt
    -0.08
    åŁºåľ°
    -0.08
    æ¦ľ
    -0.07
    æĽ¿ä»£
    -0.07
    æ¯ĶæĪij
    -0.07
    POSITIVE LOGITS
    æľ¬èº«
    0.12
    ä¸Ģå¦Ĥ
    0.12
    ä¹Łæĺ¯å¦ĤæѤ
    0.12
     itself
    0.12
    éļıä¹ĭ
    0.11
    缸åºĶ
    0.11
    çļĦ人çĶŁ
    0.10
    æľ¬äºº
    0.10
    æľ¬èº«çļĦ
    0.10
    ä¸Ģæł·
    0.10
    Activations Density 0.087%

    No Known Activations