© 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. 4073
    Prev
    Next
    INDEX
    Explanations

    and using

    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
    å¼ĥ
    -0.10
    éļ¾æĢª
    -0.10
    .$.
    -0.10
    èļĮ
    -0.10
    ä½Ĩè¿Ļ
    -0.10
    éĢļè¡Į
    -0.09
    ä¸į该
    -0.09
    æ¬
    -0.09
    èĢĮè¿Ļ
    -0.09
    大大æıIJé«ĺ
    -0.09
    POSITIVE LOGITS
    uat
    0.10
    cou
    0.10
    urt
    0.09
    裾
    0.09
    rint
    0.09
     cou
    0.08
    port
    0.08
    çĶŁåij½åĬĽ
    0.08
    4
    0.08
     coupled
    0.08
    Activations Density 0.148%

    No Known Activations