© 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. 33898
    Prev
    Next
    INDEX
    Explanations

    http, author, licensing

    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
    汧
    -0.09
     Lynn
    -0.09
    ä½Ľ
    -0.08
    æ³¼
    -0.08
    绣
    -0.08
    íķĻêµIJ
    -0.08
    缴å±ŀ
    -0.08
    足
    -0.08
    çĹĬ
    -0.08
    åĢ¾
    -0.08
    POSITIVE LOGITS
    æĥħ趣
    0.10
     fore
    0.10
    ä¸įå°½
    0.10
    emed
    0.10
    讪
    0.09
    ega
    0.09
    樨
    0.09
     Steph
    0.09
    _ATOMIC
    0.09
    elu
    0.08
    Activations Density 0.015%

    No Known Activations