© 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. 52451
    Prev
    Next
    INDEX
    Explanations

    we all followed by a verb

    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
     Paras
    -0.10
    иÑģк
    -0.10
    èļº
    -0.09
    ä¹Łè®©
    -0.09
    使人
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    ARRANT
    -0.08
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.08
    æľ¬äºº
    -0.08
    èŀ½
    -0.08
    POSITIVE LOGITS
    verständlich
    0.11
    uded
    0.09
    äºijéĽĨ
    0.09
    çŀ©
    0.09
    baugh
    0.09
     Integrity
    0.08
    mez
    0.08
    è§īå¾Ĺ
    0.08
    ading
    0.08
     menos
    0.08
    Activations Density 0.013%

    No Known Activations