© 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. 19085
    Prev
    Next
    INDEX
    Explanations

    make use of

    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
    åıĤ
    -0.10
    æĢ»æľī
    -0.09
    å°±è¿Ļä¹Ī
    -0.09
    .nl
    -0.08
    èį»
    -0.08
    Ùħات
    -0.08
    æģ¸
    -0.08
    _THROW
    -0.08
    å°±è¿Ļæł·
    -0.08
    anje
    -0.08
    POSITIVE LOGITS
    æģ¯
    0.09
    ëĭ´
    0.09
    å¹´åºķåīį
    0.09
    egin
    0.08
    maker
    0.08
    ionario
    0.08
    grim
    0.08
    ä¸įå°ıå¿ĥ
    0.08
     entirety
    0.08
    è·ĸ
    0.08
    Activations Density 0.048%

    No Known Activations