© 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. 10761
    Prev
    Next
    INDEX
    Explanations

    mail domains and bot mentions

    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
    er
    -0.09
    æĬļ
    -0.09
    缴è¾ĸ
    -0.09
    dera
    -0.08
    ack
    -0.08
    stead
    -0.08
    èĨĿ
    -0.08
    æĢ§åij½
    -0.07
    åĨįä¹Ł
    -0.07
    æĹ·
    -0.07
    POSITIVE LOGITS
    iced
    0.10
    ä¸Ģå¥Ĺ
    0.09
    ائÙħ
    0.09
    edList
    0.08
    两åıª
    0.08
    idos
    0.08
    é¦
    0.08
    atedRoute
    0.08
    simd
    0.08
    ç¥ĸåĽ½
    0.08
    Activations Density 0.002%

    No Known Activations