© 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. 22681
    Prev
    Next
    INDEX
    Explanations

    to me, this

    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
    ocity
    -0.08
    aviour
    -0.08
    rip
    -0.08
    为ä¹ĭ
    -0.08
    itim
    -0.08
    rea
    -0.08
     mad
    -0.08
     vra
    -0.08
    /or
    -0.08
    iosity
    -0.08
    POSITIVE LOGITS
    è¿Ļå°±æĺ¯
    0.12
    ç»ıå¼Ģ
    0.09
    æĦıä¹ī
    0.09
    symbols
    0.09
    exter
    0.08
    èĢĮè¨Ģ
    0.08
    çĮ¥
    0.08
    æĿ¥è¯´
    0.08
    ä»Ģä¹Īæĺ¯
    0.08
    å¾Ģäºĭ
    0.08
    Activations Density 0.015%

    No Known Activations