© 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. 33135
    Prev
    Next
    INDEX
    Explanations

    qualities and states

    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
     ÑĤакиÑħ
    -0.08
    nox
    -0.08
    æĪijèĩªå·±
    -0.08
    edImage
    -0.08
    ros
    -0.08
    though
    -0.08
    odef
    -0.07
     Peach
    -0.07
    etre
    -0.07
    /her
    -0.07
    POSITIVE LOGITS
     ÙĦÙĦغاÙĬØ©
    0.17
     enough
    0.17
     جدا
    0.16
    å¾Ĺå¾Ī
    0.13
    Enough
    0.12
     nhất
    0.12
    ä¸Ķ
    0.11
    çļĦä¸ĢéĿ¢
    0.11
    ãģĭãģ¤
    0.11
    èµ·æĿ¥
    0.11
    Activations Density 0.684%

    No Known Activations