© 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. 1891
    Prev
    Next
    INDEX
    Explanations

    quoted speech start

    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
    ection
    -0.10
    lander
    -0.09
    _AdjustorThunk
    -0.09
    æĭ¢
    -0.09
    éĤĽ
    -0.09
    éĺ»åĬĽ
    -0.08
    ecret
    -0.08
    רצ
    -0.08
    è°¨
    -0.08
    çij¾
    -0.08
    POSITIVE LOGITS
    ï¼ļ“
    0.10
    “
    0.09
     tor
    0.08
     Roe
    0.08
    åģĪ
    0.08
    grim
    0.08
     Nach
    0.08
    “(
    0.08
     “
    0.08
    weit
    0.07
    Activations Density 0.033%

    No Known Activations