© 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. 11919
    Prev
    Next
    INDEX
    Explanations

    presence

    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
    starter
    -0.10
    ÑĢин
    -0.10
    Freedom
    -0.09
    ommen
    -0.08
    owell
    -0.08
    eries
    -0.08
    iled
    -0.08
    æģ©
    -0.08
    tek
    -0.08
    é¢ı
    -0.08
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.11
    åĴĮåıijå±ķ
    0.11
    OrElse
    0.10
    ä¸İåıijå±ķ
    0.10
    ä¾®
    0.09
    éĶ·
    0.09
     khắp
    0.09
    .Serialize
    0.09
     налиÑĩии
    0.09
    äºĨä¸Ģ个
    0.08
    Activations Density 0.051%

    No Known Activations