© 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. 7063
    Prev
    Next
    INDEX
    Explanations

    atrial

    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
     bill
    -0.10
    ase
    -0.09
    BaseContext
    -0.09
    ema
    -0.09
    __$
    -0.09
    éģij
    -0.09
    ctx
    -0.08
    ä¸ŀ
    -0.08
    éĢĥçĶŁ
    -0.08
    秩
    -0.08
    POSITIVE LOGITS
    建设åĴĮ
    0.09
    iffin
    0.08
    亥
    0.08
    æĮĿ
    0.08
    裡
    0.08
    _activate
    0.08
     widened
    0.08
    å¤įåħ´
    0.08
    ROAD
    0.08
    (Py
    0.08
    Activations Density 0.218%

    No Known Activations