© 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. 49289
    Prev
    Next
    INDEX
    Explanations

    Italian organization names

    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
    幺
    -0.10
    å¾ħãģ¡
    -0.09
    åİŁæĸĩåľ°åĿĢ
    -0.09
    Ãło
    -0.09
    Ỿ
    -0.09
    sert
    -0.08
    orary
    -0.08
    ponder
    -0.08
    è¾Ľåĭ¤
    -0.08
     оÑĢи
    -0.08
    POSITIVE LOGITS
    ãĢħ
    0.09
    ä½łåĸľæ¬¢
    0.09
    é¼ĵ
    0.08
     dÃłng
    0.08
     коÑĤоÑĢÑĭм
    0.08
    ä¸įçĦ¶
    0.08
    _cli
    0.08
    _EXTERN
    0.08
    mé
    0.08
    èĭ«
    0.08
    Activations Density 0.097%

    No Known Activations