© 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. 9850
    Prev
    Next
    INDEX
    Explanations

    technology and its provider

    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
    åºľ
    -0.09
    éĢļ车
    -0.09
    3
    -0.08
    å¾Ģè¿Ķ
    -0.08
    ibox
    -0.08
    ç½ijç«Ļ建设
    -0.08
    4
    -0.08
    主管
    -0.08
    0
    -0.08
    à¸ģà¸Ńà¸ĩ
    -0.08
    POSITIVE LOGITS
    èĵį
    0.11
    èĮĤ
    0.10
    èļ¬
    0.10
    è´¡çĮ®
    0.10
    èĬĭ
    0.10
    оÑģÑĮ
    0.09
    åľ¨ä¸Ĭæµ·
    0.09
    éģįåıĬ
    0.09
    _SOUND
    0.09
    èĮĶ
    0.09
    Activations Density 0.106%

    No Known Activations