© 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. 27666
    Prev
    Next
    INDEX
    Explanations

    fresh cream and skin

    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
    ç³ł
    -0.11
    invisible
    -0.11
     invisible
    -0.10
    çĩĬ
    -0.10
    æĹłå£°
    -0.10
    STALL
    -0.10
    ç»Ī身
    -0.09
    é»ĺé»ĺ
    -0.09
    èĹıçĿĢ
    -0.09
    åİĨåı²æĤłä¹ħ
    -0.09
    POSITIVE LOGITS
    åĩºçĤī
    0.18
    æĸ°é²ľ
    0.16
     fresh
    0.16
    fresh
    0.14
     Fresh
    0.13
     fres
    0.13
    Fresh
    0.13
    é²ľ
    0.13
     freshness
    0.13
    æ¯ıä¸Ģ天
    0.11
    Activations Density 0.032%

    No Known Activations