© 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. 9444
    Prev
    Next
    INDEX
    Explanations

    pertain to

    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
    pedia
    -0.10
    leine
    -0.10
    èĥ¥
    -0.10
    åĨ³ä¸į
    -0.09
    paces
    -0.09
    اص
    -0.09
    uet
    -0.09
    allah
    -0.09
    ı
    -0.08
    quires
    -0.08
    POSITIVE LOGITS
    urbation
    0.12
    ensive
    0.09
    té
    0.09
    æµĶ
    0.09
    esa
    0.09
    渰
    0.09
    uso
    0.09
    eso
    0.09
    çħ§é¡¾
    0.09
    fect
    0.08
    Activations Density 0.028%

    No Known Activations