© 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. 2433
    Prev
    Next
    INDEX
    Explanations

    community features and more

    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
    裨
    -0.11
    åĢĴæĺ¯
    -0.09
    åĸ»
    -0.09
    鸳
    -0.09
    -launch
    -0.09
    åīįèĢħ
    -0.08
    ä¹Łå°±
    -0.08
    主ä½ĵ
    -0.08
    åĢº
    -0.08
    launch
    -0.08
    POSITIVE LOGITS
    å¿łå®ŀ
    0.10
    çįł
    0.09
    çķĽ
    0.09
    éĶ»éĢł
    0.09
    inton
    0.09
     Dam
    0.09
    èIJĮ
    0.08
    廳
    0.08
    åıĭè°Ĭ
    0.08
    mach
    0.08
    Activations Density 0.042%

    No Known Activations