© 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. 51161
    Prev
    Next
    INDEX
    Explanations

    ultimate fighting

    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
     Enough
    -0.09
    osto
    -0.08
     enough
    -0.08
    足
    -0.08
    å¾Īéĩįè¦ģ
    -0.08
    å¾Īæ·±
    -0.08
    ald
    -0.08
    Synopsis
    -0.07
    祸
    -0.07
    å¾Ī好
    -0.07
    POSITIVE LOGITS
    avra
    0.10
    æĮijæĪĺ
    0.10
    ILITY
    0.10
     ÑĢеж
    0.10
    æĹĥ
    0.10
    retch
    0.09
    ucher
    0.09
    kits
    0.09
    odate
    0.09
    IMATE
    0.09
    Activations Density 0.009%

    No Known Activations