© 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. 3932
    Prev
    Next
    INDEX
    Explanations

    system restarted

    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
    æĪijåĸľæ¬¢
    -0.09
    æ³¥
    -0.09
    大åıij
    -0.09
    åĿļå®ļä¸į
    -0.08
    åħ¨è¿ĩç¨ĭ
    -0.08
    iero
    -0.08
    æīįæĺ¯çľŁæŃ£
    -0.08
    褪
    -0.08
    .Dec
    -0.08
    EDITOR
    -0.08
    POSITIVE LOGITS
    ä¿¡ç®±
    0.12
    åį´åıijçİ°
    0.12
    åıijçİ°
    0.11
    åıijè§ī
    0.10
    æ£ĢæŁ¥
    0.10
    第äºĮ天
    0.10
    åħ¥æīĭ
    0.09
    å·¡æŁ¥
    0.09
     ÑģÑĤал
    0.09
    æĹ©ä¸Ĭ
    0.09
    Activations Density 0.089%

    No Known Activations