© 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. 17360
    Prev
    Next
    INDEX
    Explanations

    finally happened

    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
    继ç»Ńä¿ĿæĮģ
    -0.10
    ãģĻãģ§ãģ«
    -0.10
    å¾Īå¿«
    -0.10
    å·²ç»ıæľī
    -0.10
    å¾Īå¿«å°±
    -0.10
    çªģçĦ¶
    -0.10
    æľªæĿ¥
    -0.10
    è¿ħéĢŁ
    -0.09
     Already
    -0.09
    oup
    -0.09
    POSITIVE LOGITS
    ç»Īäºİ
    0.17
     finally
    0.14
    çµĤæĸ¼
    0.13
    羣æŃ£
    0.13
    æĢ»ç®Ĺ
    0.12
    羣æŃ£çļĦ
    0.11
    Finally
    0.10
    finally
    0.10
     truly
    0.09
    åľľ
    0.09
    Activations Density 0.045%

    No Known Activations