© 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. 51071
    Prev
    Next
    INDEX
    Explanations

    review or feedback

    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
     ÙħÙĨÙĩ
    -0.09
    çļĦåĬ¨ä½ľ
    -0.09
    abus
    -0.09
    纸ä¸Ĭ
    -0.08
    ä¿ĺ
    -0.08
    åĬ¨ä½ľ
    -0.08
     Freund
    -0.08
    .page
    -0.08
     дела
    -0.08
    仲
    -0.08
    POSITIVE LOGITS
    åıįé¦Ī
    0.19
     feedback
    0.17
     Feedback
    0.17
    Feedback
    0.15
    è¯Ħä»·
    0.14
    æī¹è¯Ħ
    0.14
     оÑĤз
    0.14
    .feedback
    0.14
    好è¯Ħ
    0.13
    feedback
    0.12
    Activations Density 0.074%

    No Known Activations