© 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. 17594
    Prev
    Next
    INDEX
    Explanations

    views of scenery

    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
    isman
    -0.10
    .pad
    -0.09
    ame
    -0.09
    åĪĸ
    -0.08
    ÑĥÑĤ
    -0.08
    onym
    -0.08
    没æľīåĬŀæ³ķ
    -0.08
    稳åģ¥
    -0.08
    趣åij³
    -0.08
    horn
    -0.08
    POSITIVE LOGITS
    _ARCHIVE
    0.09
    宪
    0.09
    ouser
    0.09
    akes
    0.09
    UCE
    0.09
    éĢ¼
    0.08
    æĬ¥çº¸
    0.08
    åıĸèĥľ
    0.08
    BUF
    0.08
     Replica
    0.08
    Activations Density 0.008%

    No Known Activations