© 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. 63195
    Prev
    Next
    INDEX
    Explanations

    KO Koenig effect eper der

    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
    çĮİ
    -0.10
    æħ·æħ¨
    -0.09
    éĻĽ
    -0.09
    èĴĻ
    -0.09
    æī¹åıij
    -0.08
    第ä¸Ģéĥ¨
    -0.08
     bonus
    -0.08
    寥
    -0.08
    eyed
    -0.08
    EqualTo
    -0.08
    POSITIVE LOGITS
    ç¦ģå¿Į
    0.10
    ä¹ĭæĦı
    0.09
    侮辱
    0.09
    åıijçİ°èĩªå·±
    0.09
    çŃ¾
    0.09
    ams
    0.08
    éĻªä½ł
    0.08
    æ£ķèī²
    0.08
    ä¹ĭ举
    0.08
    ä¾Ľæļĸ
    0.08
    Activations Density 0.019%

    No Known Activations