© 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. 56063
    Prev
    Next
    INDEX
    Explanations

    ways to improve or manage

    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
     Raz
    -0.09
    åĪĪ
    -0.09
    åħij
    -0.08
    Locker
    -0.08
    çļĦä¸Ģç§į
    -0.08
    å°±åºĶ该
    -0.08
    æľīä¸Ģç§į
    -0.08
    æĦıåij³
    -0.08
    äºĨ许å¤ļ
    -0.08
    æľīä»Ģä¹Ī
    -0.08
    POSITIVE LOGITS
    éĻįä½İæĪIJæľ¬
    0.11
    åĪºæ¿Ģ
    0.11
    åĨĻçĿĢ
    0.10
    è¾ħåĬ©
    0.10
    åł¡
    0.10
    çľģéĴ±
    0.10
    å¢ŀè¿Ľ
    0.10
    arrow
    0.09
    ä¸į让
    0.09
    è¿Ļå¼ł
    0.09
    Activations Density 0.264%

    No Known Activations