© 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. 18048
    Prev
    Next
    INDEX
    Explanations

    DP, policy, TDD, MLS

    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
    éĽĨåĽ¢èĤ¡ä»½
    -0.11
    å·²ä¹ħçļĦ
    -0.10
    ä¸Ģåı£æ°Ķ
    -0.09
    è§ģåĪ°
    -0.09
    缮çĿ¹
    -0.08
    ĥĿ
    -0.08
    atest
    -0.08
    ä¸įä»ħèĥ½
    -0.08
    ä¸įåĥħ
    -0.08
    æĭ¥æľī
    -0.08
    POSITIVE LOGITS
    ä¹ĭç±»çļĦ
    0.11
    è¿ĻäºĽä¸ľè¥¿
    0.10
    ä¹ĭç±»
    0.10
    ein
    0.10
     etc
    0.09
    ãģĿãģ®ä»ĸ
    0.09
    太å¤ļ
    0.09
    .startActivity
    0.08
    phans
    0.08
    ulin
    0.08
    Activations Density 1.373%

    No Known Activations