© 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. 10990
    Prev
    Next
    INDEX
    Explanations

    fertility or validation issues

    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
     Boeh
    -0.10
    æĭĽ
    -0.09
    åĨįè§ģ
    -0.09
    æŃ£å½ĵ
    -0.09
    _MATH
    -0.09
    uela
    -0.09
    æ¥ŀ
    -0.09
    inges
    -0.09
    /Framework
    -0.09
    æݺ
    -0.09
    POSITIVE LOGITS
    æ¼ı
    0.11
    æ°¸ä¹ħ
    0.10
    par
    0.09
    çĽĨ
    0.09
    éĶĻè¿ĩäºĨ
    0.09
    mina
    0.09
    è¾ĵåįµç®¡
    0.08
    æĢģ
    0.08
    èĻ¹
    0.08
    èĮ´
    0.08
    Activations Density 0.167%

    No Known Activations