© 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. 58492
    Prev
    Next
    INDEX
    Explanations

    imaging device components

    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
    æĪIJ人
    -0.13
    大人
    -0.10
    éĻĶ
    -0.10
    .vs
    -0.10
     AUTHORS
    -0.09
    tero
    -0.09
    akh
    -0.09
    ä¸Ģ段
    -0.09
    ç«ĭ足
    -0.09
    åıĹä¸įäºĨ
    -0.09
    POSITIVE LOGITS
    æ±°
    0.08
    æĬĹæ°§åĮĸ
    0.08
     pile
    0.08
    çŃł
    0.08
    æĮij
    0.08
    äºĭåIJİ
    0.08
    ilon
    0.07
     Areas
    0.07
    Areas
    0.07
    ants
    0.07
    Activations Density 0.068%

    No Known Activations