© 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. 31012
    Prev
    Next
    INDEX
    Explanations

    fraction 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
    ç®ĢåİĨ
    -0.09
    æŀŀ
    -0.09
    èı²
    -0.08
    adders
    -0.08
    ä¿®æŃ£
    -0.08
     foreground
    -0.08
     Pan
    -0.08
    wheel
    -0.08
    äºĪ以
    -0.07
    umd
    -0.07
    POSITIVE LOGITS
    ä¸ĢåįĬ
    0.17
    ä¸īåĪĨä¹ĭä¸Ģ
    0.14
    ä¸įåĪ°
    0.11
     полов
    0.11
    ä¸įåıĬ
    0.10
    ä¸Ģéĥ¨åĪĨ
    0.10
    æĿĥéĩį
    0.10
    ynth
    0.10
    ë³´ëĭ¤
    0.10
    ingo
    0.09
    Activations Density 0.057%

    No Known Activations