© 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. 31659
    Prev
    Next
    INDEX
    Explanations

    around the corner

    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
    åı¯æĥľ
    -0.09
    ç²Ł
    -0.09
    温æ³ī
    -0.09
    achi
    -0.08
    ÑıÑģ
    -0.08
    çķĮ
    -0.08
    äºĭä¸ļ
    -0.08
     décid
    -0.08
    ä¸įå½±åĵį
    -0.08
    ãĤĤãģ¡ãĤį
    -0.08
    POSITIVE LOGITS
    æĽ´å¤ļä¿¡æģ¯
    0.10
    对æĪij
    0.09
    ä½Ĩå®ĥ
    0.08
    èijĨ
    0.08
    åĸ§
    0.08
    shal
    0.08
     forth
    0.08
    èĢĮæĿ¥
    0.08
    ãģ¤ãĤĤãĤĬ
    0.08
    åĩºè·¯
    0.08
    Activations Density 0.005%

    No Known Activations