© 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. 36281
    Prev
    Next
    INDEX
    Explanations

    body-worn cameras

    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
    鸢
    -0.10
    yang
    -0.09
    âĸ¸
    -0.09
    yre
    -0.09
    èij¡èIJĦéħĴ
    -0.09
     каÑĩ
    -0.09
    outu
    -0.09
    /code
    -0.08
    .GetObject
    -0.08
     UClass
    -0.08
    POSITIVE LOGITS
    èĥ¸åīį
    0.10
    èĩªå¾ĭ
    0.08
    æĪĺæĸĹåĬĽ
    0.08
    æµĵæµĵ
    0.08
    kee
    0.08
    åĬ²
    0.08
    é«ĺé¢ij
    0.08
    çĦĬ
    0.08
     rpt
    0.08
     HUD
    0.08
    Activations Density 0.168%

    No Known Activations