© 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. 56907
    Prev
    Next
    INDEX
    Explanations

    missed opportunity

    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
    OTS
    -0.10
    路桥
    -0.09
    [__
    -0.09
    UNC
    -0.09
     kicker
    -0.09
    åħħ足çļĦ
    -0.09
    åį¸
    -0.09
    æ·±åĪĩ
    -0.09
    è·¬
    -0.09
    ibu
    -0.09
    POSITIVE LOGITS
    çĿĢä»ĸ
    0.09
    èĩ´
    0.09
    æĭĽåĭŁ
    0.08
    æĹłä¸į
    0.08
    pak
    0.08
    rs
    0.08
    çĶ³æĬ¥
    0.08
    aggregate
    0.08
    èĴ
    0.08
    çī¹æĿĥ
    0.08
    Activations Density 0.027%

    No Known Activations