© 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. 27727
    Prev
    Next
    INDEX
    Explanations

    foreign concepts or entities

    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
    ä¸įå°½
    -0.10
    ddy
    -0.09
     inquiry
    -0.09
    åŃ£
    -0.09
    å²Ķ
    -0.09
    å±ŀäºİèĩªå·±
    -0.09
    亮
    -0.08
    isches
    -0.08
     Inquiry
    -0.08
    izen
    -0.08
    POSITIVE LOGITS
     alien
    0.13
    æİ¥åľ°æ°Ķ
    0.11
    alien
    0.10
    éĿ¢åŃĶ
    0.10
    群ä¼Ĺ
    0.10
    å¾Īå¤ļçݩ家
    0.10
    ä¹ĺçĶ¨è½¦
    0.10
    è´´è¿ij
    0.09
    èħIJ
    0.09
     плаÑģÑĤ
    0.09
    Activations Density 0.060%

    No Known Activations