© 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. 38780
    Prev
    Next
    INDEX
    Explanations

    click on

    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
    寸
    -0.11
    ä¸Ńåħ³
    -0.10
    ä¸įæĸŃæıIJåįĩ
    -0.09
    滨海
    -0.09
    å¯Ŀ
    -0.09
    丰å¯Į
    -0.09
    cciones
    -0.09
    ãģĦãģ¤
    -0.09
    wij
    -0.08
    ä¸įæĸŃæıIJé«ĺ
    -0.08
    POSITIVE LOGITS
    åĽ¢
    0.09
    è½®æµģ
    0.09
    ServiceProvider
    0.08
    çıĤ
    0.08
    综åIJĪå®ŀåĬĽ
    0.08
    à¸ģำ
    0.08
    åı©
    0.08
    çĻ¾èĬ±
    0.08
     prominence
    0.08
    priv
    0.07
    Activations Density 0.032%

    No Known Activations