© 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. 63116
    Prev
    Next
    INDEX
    Explanations

    copyright notices and licenses

    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
    å³Ń
    -0.10
    ught
    -0.09
     долж
    -0.09
    éĶ»çĤ¼
    -0.09
    éģ½
    -0.08
    åĿİ
    -0.08
    .ticket
    -0.08
     sharpen
    -0.08
    æİ¥çĿĢ
    -0.08
    åı¯è¡Į
    -0.08
    POSITIVE LOGITS
    æ´»è·ĥ
    0.11
    åıĤä¸İèĢħ
    0.10
    éĢŁåº¦å¿«
    0.09
    anan
    0.09
    è°ģéĥ½
    0.09
    ãĥ¬ãĥĵ
    0.09
    为主è¦ģ
    0.09
    èŁł
    0.09
    å¤ĸéĥ¨
    0.08
    æļĹæļĹ
    0.08
    Activations Density 0.001%

    No Known Activations