© 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. 20686
    Prev
    Next
    INDEX
    Explanations

    wiring and cables

    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
    igua
    -0.09
    产åĵģçłĶåıij
    -0.08
    åĵģ
    -0.08
    å±±åĿ¡
    -0.08
    Spin
    -0.08
    å°ıåŀĭ
    -0.08
    imore
    -0.08
    ContentLoaded
    -0.08
    closing
    -0.08
     Weiss
    -0.08
    POSITIVE LOGITS
    çĶµçº¿
    0.17
     wiring
    0.16
    çĶµç¼Ĩ
    0.15
     Wiring
    0.14
     wires
    0.13
    æķ·
    0.13
    éĵºè®¾
    0.12
    å¸ĥ
    0.12
     cables
    0.12
     wire
    0.11
    Activations Density 0.299%

    No Known Activations