© 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. 61972
    Prev
    Next
    INDEX
    Explanations

    hosting services and accounts

    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
    oku
    -0.10
    uku
    -0.09
    åıįè¿ĩæĿ¥
    -0.09
    dia
    -0.08
    å¾ĹåĪĨ
    -0.08
    åĽŀæĥ³
    -0.08
    éĵį
    -0.08
    5
    -0.08
    4
    -0.08
    ServletContext
    -0.08
    POSITIVE LOGITS
    kre
    0.10
    ICON
    0.10
    BAR
    0.10
    _IC
    0.09
    _icons
    0.09
    éĵ¨
    0.09
    stars
    0.09
    èµ°ç§ģ
    0.09
    _ICON
    0.09
     icons
    0.09
    Activations Density 0.033%

    No Known Activations