© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52435
    Prev
    Next
    INDEX
    Explanations

    nail polish

    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
    æŃ£åĢ¼
    -0.08
    å®ľ
    -0.08
    æİĸ
    -0.08
    æŀĦéĢł
    -0.08
     allot
    -0.08
    å®ģæĦ¿
    -0.08
    alia
    -0.08
     Hun
    -0.08
    reset
    -0.07
    oup
    -0.07
    POSITIVE LOGITS
    èļĢ
    0.12
    asil
    0.10
    /o
    0.09
    spe
    0.09
    edImage
    0.09
    stry
    0.09
    ered
    0.09
    _EMIT
    0.09
    eron
    0.08
    溥
    0.08
    Activations Density 0.019%

    No Known Activations