© 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. 50503
    Prev
    Next
    INDEX
    Explanations

    and have

    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
    å¹²èĦĨ
    -0.09
    举è¡ĮäºĨ
    -0.09
    æĻº
    -0.08
    举åĬŀäºĨ
    -0.08
    å¢ĥåĨħ
    -0.08
    OfType
    -0.08
    _idxs
    -0.08
    仪表
    -0.08
     Delicious
    -0.07
     ÑĥдалоÑģÑĮ
    -0.07
    POSITIVE LOGITS
    æ¶Ī
    0.11
    perator
    0.10
    çļĦæĦıä¹ī
    0.09
    ä¿Ŀè¯ģ
    0.09
    éģ¿åħį
    0.09
    æ¯ĶåĪĨ
    0.09
    taire
    0.09
    cene
    0.09
    aders
    0.08
    çŁ¥éģĵèĩªå·±
    0.08
    Activations Density 0.094%

    No Known Activations