© 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. 63636
    Prev
    Next
    INDEX
    Explanations

    mail 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
     Garr
    -0.09
    duc
    -0.09
    ignum
    -0.08
    éĴī
    -0.08
    对ä¸ŃåĽ½
    -0.08
    红æĹĹ
    -0.08
    è¾Ķ
    -0.08
     Tick
    -0.08
    oby
    -0.07
     barn
    -0.07
    POSITIVE LOGITS
    é©·
    0.10
    åķĨä¸ļ
    0.10
    åĴĮå®ĮåĸĦ
    0.10
    .variable
    0.10
    åįİ丽
    0.10
    ä¸įä¸ĭ
    0.09
    èĩĥ
    0.09
    éķ¿æ²Ļå¸Ĥ
    0.09
    ä¸įèµ·
    0.09
    emm
    0.09
    Activations Density 0.002%

    No Known Activations