© 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. 62182
    Prev
    Next
    INDEX
    Explanations

    but, however, while

    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
    æ³°å±±
    -0.09
    没æľīä»Ģä¹Ī
    -0.09
    类似çļĦ
    -0.09
    lg
    -0.08
     termin
    -0.08
    ä¸įåºĶ该
    -0.08
    lm
    -0.08
    LineNumber
    -0.08
    ä¹Łå¥½
    -0.08
    åıĪ好
    -0.08
    POSITIVE LOGITS
    åģļä¸įåĪ°
    0.15
    èĥ½åģļåĪ°
    0.14
    åģļåĪ°
    0.13
    羣æŃ£åģļåĪ°
    0.13
    è¿Ļä¹Īåģļ
    0.11
    åģļåĪ°äºĨ
    0.11
    æĢİä¹Īåģļ
    0.11
    çĿ£ä¿ĥ
    0.10
    éļ¾
    0.10
     unpopular
    0.10
    Activations Density 0.091%

    No Known Activations