© 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. 53989
    Prev
    Next
    INDEX
    Explanations

    sensory perception and detection

    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
    çļĦçŃĶæ¡Ī
    -0.10
    blink
    -0.10
    æı©
    -0.09
    ouch
    -0.09
    gli
    -0.08
    ç»Ī
    -0.08
    橱
    -0.08
    å¯Ĩ
    -0.08
     Blink
    -0.08
    rh
    -0.08
    POSITIVE LOGITS
    æ£ł
    0.12
    æĦŁè§īåĪ°
    0.12
     thấy
    0.11
    çľĭè§ģ
    0.11
    çľĭåĪ°äºĨ
    0.11
    èĥ½çľĭåĪ°
    0.11
    å¯Łè§ī
    0.10
    尾巴
    0.10
    æĦŁçŁ¥
    0.10
    æĦŁåıĹåĪ°
    0.10
    Activations Density 0.177%

    No Known Activations