© 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. 31031
    Prev
    Next
    INDEX
    Explanations

    make a case

    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
    .generated
    -0.10
    æİ¥
    -0.09
     repreh
    -0.09
    æĿī
    -0.09
    éŀįå±±
    -0.09
    Stmt
    -0.08
    _ste
    -0.08
    è·Łè¿Ľ
    -0.08
    âm
    -0.08
    æ·±åıĹ
    -0.08
    POSITIVE LOGITS
    è¯ģæĺİ
    0.16
    论è¯ģ
    0.13
     convinc
    0.12
    èŃīæĺİ
    0.12
    arguments
    0.11
    è¯ģæį®
    0.11
     arguments
    0.11
    çłĶ究表æĺİ
    0.11
     показ
    0.11
     argument
    0.11
    Activations Density 0.091%

    No Known Activations