© 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. 5547
    Prev
    Next
    INDEX
    Explanations

    fill in the blank

    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
    mens
    -0.09
    å®ģ
    -0.09
    å±Ģ
    -0.09
    管å±Ģ
    -0.09
    éĴ»çłĶ
    -0.08
    agency
    -0.08
    æĸĽ
    -0.08
     squash
    -0.08
    .face
    -0.08
    bung
    -0.08
    POSITIVE LOGITS
    ä¸ķ
    0.10
    稻
    0.10
    æ´»åĬ¨ä¸Ń
    0.10
    åįģåĪĨéĩįè¦ģ
    0.10
    æ²¹èĦĤ
    0.10
    ä¸Ģè¡Į
    0.09
    ç»ıåħ¸
    0.09
    _expression
    0.09
    èĢģåħµ
    0.09
    è¦ģ说
    0.08
    Activations Density 0.028%

    No Known Activations