© 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. 1363
    Prev
    Next
    INDEX
    Explanations

    signing new contracts

    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
    ä¼ĺ
    -0.09
    åħľ
    -0.08
    ä¸Ģå¹ķ
    -0.08
    éĽĨå¸Ĥ
    -0.08
    _MARKER
    -0.08
    æ¯ĶåĪ©
    -0.08
    ä¸ĭåįķ
    -0.08
    èĿĩ
    -0.08
    UpDown
    -0.08
     ÑģоÑģÑĤ
    -0.08
    POSITIVE LOGITS
    åIJĪåIJĮ
    0.17
    åĬ³åĬ¨åIJĪåIJĮ
    0.17
     contracts
    0.16
     contract
    0.16
    çŃ¾è®¢
    0.15
    çŃ¾çº¦
    0.14
    (contract
    0.14
    åIJĪ约
    0.14
    å¥ij约
    0.14
    å¥ij
    0.14
    Activations Density 0.121%

    No Known Activations