© 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. 26795
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

    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
    éĹ³
    -0.10
    å°±æĺ¯åľ¨
    -0.09
    沧
    -0.09
    phasis
    -0.08
    ansi
    -0.08
     Tud
    -0.08
    anke
    -0.08
    ç²²
    -0.08
     Noon
    -0.08
    æ·¡åĮĸ
    -0.08
    POSITIVE LOGITS
    衬
    0.12
    对她
    0.11
    è°Ģ
    0.10
    ç´§å¯Ĩ
    0.10
    è¶Ĭ好
    0.09
    è´´
    0.09
    åīįæīĢæľªæľī
    0.09
    éĨij
    0.09
    è¦ģç´§
    0.09
    éĽ¢ãĤĮ
    0.09
    Activations Density 0.054%

    No Known Activations