© 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. 58434
    Prev
    Next
    INDEX
    Explanations

    turn

    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
    iors
    -0.09
    åĪĨæķ£
    -0.09
    äºĨä¸Ģ份
    -0.09
    éļıä¹ĭ
    -0.09
    -drop
    -0.09
    åĩºæĿ¥äºĨ
    -0.09
    èĢĮæĪIJ
    -0.08
    常è¯Ĩ
    -0.08
    èĦ±ç¦»
    -0.08
    ç¾¤å²Ľ
    -0.08
    POSITIVE LOGITS
    è½®
    0.13
    è½®æµģ
    0.13
     оÑĩеÑĢедÑĮ
    0.12
     turn
    0.11
    æİ¥è¿ĩ
    0.11
    åıijè¨Ģ
    0.11
     turno
    0.10
    åºı
    0.10
    æŁĦ
    0.10
    _turn
    0.09
    Activations Density 0.029%

    No Known Activations