© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19531
    Prev
    Next
    INDEX
    Explanations

    asking for advice or help

    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
    ä½łåĸľæ¬¢
    -0.10
    çĮľ
    -0.09
    ä½łèĩªå·±
    -0.09
    çļĦéĤ£ä¸ª
    -0.09
    æĺ¯è°ģ
    -0.09
    ä½łè¿ĺ
    -0.09
    è¿ĻçĤ¹
    -0.09
    è§Ī
    -0.08
    å·§
    -0.08
    éĤ£åıª
    -0.08
    POSITIVE LOGITS
    è¿Ļæĺ¯æĪij
    0.10
    arme
    0.09
    каÑĤ
    0.09
     táºŃn
    0.09
    æĪijçļĦå¿ĥ
    0.09
    tablet
    0.09
    .enumer
    0.09
    .xr
    0.09
    å¸ĮæľĽèĥ½å¤Ł
    0.09
    åħ¨ãģı
    0.09
    Activations Density 0.805%

    No Known Activations