© 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. 39093
    Prev
    Next
    INDEX
    Explanations

    suffix 'ial' or word collateral

    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
    åĿª
    -0.10
    ÑģÑĤо
    -0.09
    chor
    -0.09
    çħ§
    -0.09
    /ion
    -0.08
    æļĤç¼ĵ
    -0.08
    pee
    -0.08
    ç¨ļ
    -0.08
    åĺ²ç¬ij
    -0.08
    Ñģко
    -0.08
    POSITIVE LOGITS
    顾
    0.09
    åºĸ
    0.09
    ä¸Ģç±»
    0.09
    zin
    0.08
    .ru
    0.08
    biz
    0.08
    ä¹IJ趣
    0.08
    大åºĨ
    0.08
    ä¸įç®¡ä½ł
    0.08
    黩
    0.08
    Activations Density 0.057%

    No Known Activations