© 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. 27343
    Prev
    Next
    INDEX
    Explanations

    organizations and leagues

    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
    å¾Īåĸľæ¬¢
    -0.09
     fond
    -0.09
    çĽ¸ä¿¡å¤§å®¶
    -0.09
    æĹ¥äº§
    -0.08
    åħ¬çĦ¶
    -0.08
    íĨ±
    -0.08
    Specifier
    -0.08
    weise
    -0.08
    æĶ¶åĪ°äºĨ
    -0.08
     Tanz
    -0.08
    POSITIVE LOGITS
    marvin
    0.10
    .cloud
    0.09
    ç¥ĸåĽ½
    0.09
     Ups
    0.09
    ç°ĩ
    0.09
    磫
    0.08
    æĻķ
    0.08
    пиÑģÑĮ
    0.08
    organization
    0.08
    exec
    0.08
    Activations Density 0.037%

    No Known Activations