© 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. 31016
    Prev
    Next
    INDEX
    Explanations

    mobile devices and services

    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
    ools
    -0.11
    ormal
    -0.11
    ooled
    -0.10
    ual
    -0.10
    lan
    -0.10
    åĴĮæľįåĬ¡
    -0.09
    OwnProperty
    -0.09
    æ¶Ŀ
    -0.08
    æľ¬ç½ijç«Ļ
    -0.08
    orney
    -0.08
    POSITIVE LOGITS
    -ish
    0.11
    asics
    0.10
    butt
    0.09
    /mobile
    0.09
    é¢Ķ
    0.09
    ëģĶ
    0.09
    /desktop
    0.09
    ignon
    0.09
    ités
    0.09
    kad
    0.09
    Activations Density 0.020%

    No Known Activations