© 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. 48866
    Prev
    Next
    INDEX
    Explanations

    scanned-page or @ENRON

    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
    è§ĴèIJ½
    -0.08
    åĬ¼
    -0.08
    ×ķפ
    -0.07
    è¿Ļæĸ¹éĿ¢
    -0.07
     aforementioned
    -0.07
    éľ²
    -0.07
    çīµ
    -0.07
    prm
    -0.07
    иÑĩ
    -0.07
    å°ıé¾Ļ
    -0.07
    POSITIVE LOGITS
    udeau
    0.09
    æĭį
    0.09
    åĪĨæĺİ
    0.08
    表达äºĨ
    0.08
    .TryParse
    0.08
    æ¸ij
    0.08
    	Use
    0.08
    _hot
    0.08
    rial
    0.08
    ä¸į足以
    0.08
    Activations Density 0.397%

    No Known Activations