© 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. 3960
    Prev
    Next
    INDEX
    Explanations

    eyes, tail, foot

    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
    ersed
    -0.10
    isphere
    -0.10
    èĥľä»»
    -0.10
    velle
    -0.09
    bie
    -0.09
     mates
    -0.09
    ä¼Ļä¼´
    -0.09
    fell
    -0.09
    她说
    -0.09
    ä»ĸ说
    -0.09
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.10
     hitch
    0.08
    ainless
    0.08
     اÙĦعÙħ
    0.08
    ucid
    0.08
     Hilton
    0.08
    à¸Ħà¸ĩ
    0.08
    azen
    0.08
    CED
    0.07
    å½ĵåľ°
    0.07
    Activations Density 0.048%

    No Known Activations