© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10599
    Prev
    Next
    INDEX
    Explanations

    own

    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
    2
    -0.09
    1
    -0.08
     notebook
    -0.08
    3
    -0.08
    zion
    -0.08
    eri
    -0.08
     sharpen
    -0.08
    5
    -0.08
    4
    -0.08
     recover
    -0.07
    POSITIVE LOGITS
    çĶ¨èĩªå·±çļĦ
    0.20
    èĩªå·±çļĦ
    0.19
    æľīèĩªå·±çļĦ
    0.19
    own
    0.19
    äºĨèĩªå·±çļĦ
    0.19
     own
    0.19
    èĩªæľī
    0.17
    çĭ¬èĩª
    0.16
    Own
    0.16
    èĩªè¡Į
    0.16
    Activations Density 0.298%

    No Known Activations