© 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. 62847
    Prev
    Next
    INDEX
    Explanations

    wireless mobile communications

    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
    çĿ£å¯¼
    -0.09
    åĭĥ
    -0.09
    ombat
    -0.09
    èĶļ
    -0.08
    lda
    -0.08
    åıĺåİĭ
    -0.08
    æĹłäºº
    -0.08
    PTR
    -0.08
    æĿ¥çļĦ
    -0.08
    urity
    -0.08
    POSITIVE LOGITS
    sic
    0.10
    竺
    0.09
    å¢Ĵ
    0.09
    æīĭæĦŁ
    0.09
    好æ¶Īæģ¯
    0.09
     pockets
    0.08
    SELF
    0.08
    .tick
    0.08
    iji
    0.08
    -handed
    0.08
    Activations Density 0.003%

    No Known Activations