© 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. 3653
    Prev
    Next
    INDEX
    Explanations

    hours or miles

    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
     sto
    -0.10
    æĮ¹
    -0.09
    ä»°
    -0.09
    iland
    -0.09
     lan
    -0.08
    eph
    -0.08
    èīºæľ¯åĵģ
    -0.08
    éī´
    -0.08
    ä¿ı
    -0.08
    豫
    -0.08
    POSITIVE LOGITS
    累积
    0.12
    累计
    0.12
    ä¼ĹæīĢ
    0.10
    两åįĥ
    0.09
    æķ°åįĥ
    0.09
    ç´¯
    0.09
     Hob
    0.09
    ä¿Ŀåħ»
    0.09
    积累
    0.09
    ersed
    0.09
    Activations Density 0.047%

    No Known Activations