© 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. 53914
    Prev
    Next
    INDEX
    Explanations

    email server configuration

    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»£æĽ¿
    -0.11
    åĨ²åĩ»
    -0.10
    åıĸ代
    -0.10
    _VC
    -0.09
    éĢļ车
    -0.09
     воÑģ
    -0.09
    Fonts
    -0.09
    éĽªå±±
    -0.09
    _signed
    -0.09
    åĨ²
    -0.09
    POSITIVE LOGITS
    çľĭ书
    0.10
     ent
    0.08
    MenuItem
    0.08
    éŀł
    0.08
    otime
    0.08
    åĿIJä¸ĭ
    0.08
    æļ
    0.08
    å¼ĢæĿ¥
    0.08
    YL
    0.08
    å³Ń
    0.08
    Activations Density 0.129%

    No Known Activations