© 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. 58413
    Prev
    Next
    INDEX
    Explanations

    naming or calling something

    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
     Lyons
    -0.10
    åĨį说
    -0.09
    èĻļ
    -0.09
    âķ°
    -0.08
    çļĦä¸Ģç§į
    -0.08
    ä¸ĢåıĮ
    -0.08
     Loy
    -0.08
    è±Į
    -0.08
    庸
    -0.08
     ATA
    -0.08
    POSITIVE LOGITS
    ode
    0.09
    ilen
    0.09
    ument
    0.08
    éĢĤåIJĪèĩªå·±
    0.08
    å¯ĩ
    0.08
    æįIJ
    0.08
    涧
    0.08
    ODE
    0.08
    actable
    0.08
    éĨĴ缮
    0.08
    Activations Density 0.091%

    No Known Activations