© 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. 9860
    Prev
    Next
    INDEX
    Explanations

    sprinkled on top, hair spray

    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
    æ·±åİļçļĦ
    -0.11
    ç»°
    -0.10
    å¼¯æĽ²
    -0.09
    丰ç¡ķ
    -0.09
    isposable
    -0.09
    æħ¢æħ¢çļĦ
    -0.09
    è¿İ
    -0.09
    itore
    -0.09
    ouv
    -0.08
    .commons
    -0.08
    POSITIVE LOGITS
    èIJ½åľ¨
    0.10
    ç±½
    0.09
    å²Ĺ
    0.09
    çł¾
    0.08
    éĽ³
    0.08
    çĪĨ
    0.08
    ä¸īæĺ¯
    0.08
    chy
    0.08
    èĢģ人家
    0.08
    åĽĽæĺ¯
    0.08
    Activations Density 0.005%

    No Known Activations