© 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. 62736
    Prev
    Next
    INDEX
    Explanations

    deadlines and timelines

    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
    à¸ķรา
    -0.10
    æ³°
    -0.09
    olle
    -0.08
    å°Ŀè¯ķ
    -0.08
    dal
    -0.08
     SEEK
    -0.08
    æ¦Ĥæĭ¬
    -0.08
    azor
    -0.08
    aur
    -0.08
    èł¢
    -0.08
    POSITIVE LOGITS
     deadlines
    0.15
    deadline
    0.12
    è¿Ľåº¦
    0.12
     deadline
    0.12
    æľŁéĻIJ
    0.12
    紧迫
    0.12
    èĬĤå¥ı
    0.11
     schedule
    0.11
    æĹ¥æľŁ
    0.11
    æŶéĻIJ
    0.11
    Activations Density 0.078%

    No Known Activations