© 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. 61295
    Prev
    Next
    INDEX
    Explanations

    retinal layer or outer segments

    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
    åħ«å¹´
    -0.09
    uben
    -0.09
    å±¥
    -0.09
    éĥ¨åī¯
    -0.08
    èĥĸ
    -0.08
    æ°
    -0.08
     pan
    -0.08
     англи
    -0.08
    ç¥ĵ
    -0.08
    dotenv
    -0.08
    POSITIVE LOGITS
     Zag
    0.09
    æĺŁæĺŁ
    0.09
    館
    0.09
    è¿Ļ个æŶåĢĻ
    0.08
    pixels
    0.08
    ä¼ĺéĢī
    0.08
    çĤ³
    0.08
    ç»Ń
    0.08
    éĶĻ
    0.08
    å±ıéļľ
    0.08
    Activations Density 0.325%

    No Known Activations