© 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. 2465
    Prev
    Next
    INDEX
    Explanations

    fruits and berries

    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
    èī¯
    -0.09
    Drag
    -0.08
    éľĵ
    -0.08
    空çĻ½
    -0.08
    ä»İäºĭ
    -0.08
    ople
    -0.08
    usher
    -0.08
    涯
    -0.08
     drag
    -0.08
    äºĭçī©
    -0.08
    POSITIVE LOGITS
    éĨļ
    0.10
    åij³
    0.09
    并äºİ
    0.09
    æķ´ä¸ªäºº
    0.09
     Millennium
    0.09
    èī¾æ»ĭ
    0.09
    æļĿ
    0.09
    çı¥
    0.08
    两端
    0.08
     König
    0.08
    Activations Density 0.003%

    No Known Activations