© 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. 33832
    Prev
    Next
    INDEX
    Explanations

    radio and its contexts

    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
    urer
    -0.10
    åı¦ä¸ĢåįĬ
    -0.10
    ÑģÑı
    -0.10
    累累
    -0.09
    ç£ĭ
    -0.09
    幺
    -0.09
    ä¸Ģ个个
    -0.09
    ween
    -0.09
     Turbo
    -0.09
    åĦ¿
    -0.08
    POSITIVE LOGITS
    ically
    0.13
    oola
    0.11
    oling
    0.09
    تÙĩا
    0.09
     thù
    0.09
     savvy
    0.09
    fax
    0.09
    inality
    0.08
    /video
    0.08
    ond
    0.08
    Activations Density 0.016%

    No Known Activations