© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10320
    Prev
    Next
    INDEX
    Explanations

    specific product models

    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
    ä¸ĢèĤ¡
    -0.09
    ance
    -0.09
    æİī
    -0.08
    éĢĨè¡Į
    -0.08
    nop
    -0.08
    خر
    -0.08
    管çIJĨèĢħ
    -0.08
    edx
    -0.08
    ore
    -0.08
    ä¸Ģç±»
    -0.08
    POSITIVE LOGITS
    ÂŃi
    0.10
    åı·
    0.09
    uls
    0.09
    èĻŁ
    0.09
    .getModel
    0.09
    .ObjectModel
    0.09
    .MODEL
    0.09
    .Model
    0.09
    awe
    0.09
    ivre
    0.08
    Activations Density 0.039%

    No Known Activations