© 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. 30366
    Prev
    Next
    INDEX
    Explanations

    market position and share

    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
    omes
    -0.09
    éĸ£
    -0.09
    oron
    -0.09
    iatric
    -0.08
    é¹ħ
    -0.08
    ida
    -0.08
    иж
    -0.08
    åĿıäºĭ
    -0.08
    çĭłæĬĵ
    -0.08
    esser
    -0.08
    POSITIVE LOGITS
    ooter
    0.09
    第ä¸ĢæĿ¡
    0.09
    fully
    0.09
    åĪĨæĺİ
    0.08
    âĿĸ
    0.08
    plier
    0.08
    aires
    0.08
    ä»Ĺ
    0.08
     Manit
    0.08
     Gast
    0.08
    Activations Density 0.004%

    No Known Activations