© 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. 10267
    Prev
    Next
    INDEX
    Explanations

    guitar and string instruments

    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
    èĥ¸
    -0.10
    undy
    -0.10
    æģ¶å¿ĥ
    -0.10
    éľı
    -0.09
    åħ¨è¿ĩç¨ĭ
    -0.09
    æķij
    -0.09
    éĤª
    -0.09
    éļıæŶéļı
    -0.09
    .CG
    -0.09
    鹿
    -0.09
    POSITIVE LOGITS
    çIJ´
    0.10
     deg
    0.09
    æıļ
    0.08
    交è°Ī
    0.08
    弦
    0.08
    ä¾£
    0.08
    Ļ¨
    0.08
     rop
    0.08
    oders
    0.08
    æĢĢæĬ±
    0.08
    Activations Density 0.058%

    No Known Activations