© 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. 57260
    Prev
    Next
    INDEX
    Explanations

    methylene blue, eosin Y, malachite green

    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
    elage
    -0.11
    çģ¼
    -0.10
    æľĢå¿«çļĦ
    -0.10
    åĨ·èĹı
    -0.09
    交代
    -0.09
    æĪIJçĨŁçļĦ
    -0.09
    çıŀ
    -0.09
    à°³
    -0.09
     Launcher
    -0.08
    åij¨å¹´
    -0.08
    POSITIVE LOGITS
    èī²å½©
    0.10
    èī²
    0.10
    绿èī²åıijå±ķ
    0.09
    reds
    0.09
    wer
    0.09
     dye
    0.09
    ASI
    0.09
     color
    0.08
    é¢ľèī²
    0.08
    èī³
    0.08
    Activations Density 0.144%

    No Known Activations