© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8014
    Prev
    Next
    INDEX
    Explanations

    cabin or cockpit

    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
    æľīåIJį
    -0.09
    æĥľ
    -0.09
    ths
    -0.09
    sWith
    -0.09
    åĽ½åº¦
    -0.09
     зам
    -0.08
    åĨľåİĨ
    -0.08
    åľºéĿ¢
    -0.08
    åĢĴéľī
    -0.08
    vw
    -0.08
    POSITIVE LOGITS
    åĨħçļĦ
    0.12
    éĹ·
    0.10
    olls
    0.09
    elage
    0.09
    bett
    0.09
    __("
    0.08
    bedo
    0.08
    etrics
    0.08
    积æŀģåıĤä¸İ
    0.08
    ë¦Ħ
    0.08
    Activations Density 0.013%

    No Known Activations