© 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. 34777
    Prev
    Next
    INDEX
    Explanations

    community to give, help, protection, allow

    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
    åIJ¸å¼ķ
    -0.11
    åIJ¸å¼ķäºĨ
    -0.10
    ç½ijåıĭ
    -0.09
    ese
    -0.09
    诱人
    -0.09
    éĹ³
    -0.09
    asper
    -0.08
     Cath
    -0.08
    emodel
    -0.08
     Tem
    -0.08
    POSITIVE LOGITS
    åŃº
    0.10
    ç¼Ń
    0.09
    åıįé¦Ī
    0.09
    使å¾Ĺ
    0.09
    æĬķ票
    0.09
    åIJĦè¡Į
    0.09
    ä¸įéĶĪ
    0.08
     оÑĤз
    0.08
    enton
    0.08
    åĹ·
    0.08
    Activations Density 0.132%

    No Known Activations