© 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. 21378
    Prev
    Next
    INDEX
    Explanations

    metal bands and songs

    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
    诤
    -0.11
    é£İéĻ©ç®¡çIJĨ
    -0.08
     Synd
    -0.08
     Zus
    -0.08
    好åĿı
    -0.08
    æĪ¢
    -0.08
    åı£ç¢ij
    -0.08
    èĴ¯
    -0.08
    BS
    -0.08
    icie
    -0.08
    POSITIVE LOGITS
    _interfaces
    0.10
    çľī
    0.10
    umbling
    0.09
    _activation
    0.08
    齿
    0.08
    åĪ¶åīĤ
    0.08
    .edu
    0.08
    alers
    0.08
     oud
    0.08
    æ¿Ģæ´»
    0.08
    Activations Density 0.040%

    No Known Activations