© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53569
    Prev
    Next
    INDEX
    Explanations

    lock and related words

    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
    Negative Logits
     decks
    -0.09
    liche
    -0.09
    å¼Ģåĩº
    -0.09
    é£ĵ
    -0.09
    deck
    -0.08
    isor
    -0.08
    Deck
    -0.08
    eld
    -0.08
    _deck
    -0.08
    logan
    -0.08
    POSITIVE LOGITS
    ument
    0.12
    ä½ıäºĨ
    0.11
    åľ¨ä¸Ģèµ·
    0.10
    å®ļäºĨ
    0.10
    warts
    0.10
    ìį¨
    0.10
     lẽ
    0.09
    evin
    0.09
    ering
    0.09
    gger
    0.09
    Activations Density 0.022%

    No Known Activations