© 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. 11086
    Prev
    Next
    INDEX
    Explanations

    findings revealed by imaging

    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
    ä¼ļè§īå¾Ĺ
    -0.10
    claimer
    -0.09
    æĦŁè§īèĩªå·±
    -0.09
    çĤ«èĢĢ
    -0.09
    ä¹ŁæĽ¾
    -0.09
    亲æīĭ
    -0.09
    è§īå¾Ĺèĩªå·±
    -0.09
    _parents
    -0.08
    親
    -0.08
    çŁ¥éģĵèĩªå·±
    -0.08
    POSITIVE LOGITS
    çĸij
    0.11
    çĸijä¼¼
    0.11
    åĪĿæŃ¥
    0.11
    迹象
    0.09
    åĭī强
    0.09
     unusual
    0.08
     unusually
    0.08
    å¼ķèµ·äºĨ
    0.08
    åħ¶å®ĥéĹ®é¢ĺ
    0.08
    æĢª
    0.08
    Activations Density 0.194%

    No Known Activations