© 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. 5089
    Prev
    Next
    INDEX
    Explanations

    appeal and appealing words

    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
    ç»ıèIJ¥æ´»åĬ¨
    -0.10
    HEN
    -0.09
    AMI
    -0.09
    chers
    -0.09
     możli
    -0.09
    /stat
    -0.09
    赶
    -0.08
    çħ¨
    -0.08
    æĦĢ
    -0.08
    æ´İ
    -0.08
    POSITIVE LOGITS
    ayer
    0.09
    ively
    0.09
    icking
    0.08
    older
    0.08
    acing
    0.08
    è¶Ĭæĺ¯
    0.08
    !--
    0.08
    é§
    0.08
    ì´ī
    0.08
     Twin
    0.08
    Activations Density 0.005%

    No Known Activations