© 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. 53406
    Prev
    Next
    INDEX
    Explanations

    windshield wipers

    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
    ç¾İæľ¯
    -0.09
    èį©
    -0.09
    Lit
    -0.09
    è°ħ
    -0.09
    ä¸ĩéĩĮ
    -0.09
    ivors
    -0.09
    ä½ĵè´¨
    -0.08
    çįł
    -0.08
    ewood
    -0.08
    èĭ¡
    -0.08
    POSITIVE LOGITS
    Fullscreen
    0.09
    vas
    0.09
    ISE
    0.09
    fait
    0.09
    اب
    0.09
    ìŀ¡
    0.09
    unct
    0.08
    çĭ¬è§Ĵ
    0.08
    alem
    0.08
    mom
    0.08
    Activations Density 0.001%

    No Known Activations