© 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. 38080
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    alu
    -0.09
    è¦Ĩ
    -0.09
    èĶĵ
    -0.09
    象
    -0.08
    èĤĵ
    -0.08
    aal
    -0.08
    .TryParse
    -0.08
    çĵľ
    -0.08
     bore
    -0.08
    裹
    -0.08
    POSITIVE LOGITS
    æĺİçĻ½
    0.09
    è¿Ļè¾¹
    0.09
    pé
    0.08
    éªı
    0.08
    æľ¬ç½ij
    0.08
    å¼Ł
    0.08
    embers
    0.08
    äºŃ
    0.08
     ÑĥкÑĢа
    0.08
    éĥģéĹ·
    0.08
    Activations Density 0.014%

    No Known Activations