© 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. 58920
    Prev
    Next
    INDEX
    Explanations

    win forms and winemaking

    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
    çłĶ究ä¸Ńå¿ĥ
    -0.10
    inch
    -0.10
    _POINTER
    -0.09
    ening
    -0.09
    ives
    -0.09
    ively
    -0.09
    êµ´
    -0.09
    ities
    -0.08
    磾
    -0.08
    weet
    -0.08
    POSITIVE LOGITS
    ners
    0.12
    ograd
    0.11
    itial
    0.11
    ning
    0.10
    rose
    0.10
    fred
    0.10
    xed
    0.10
    estone
    0.09
    thes
    0.09
    emaker
    0.09
    Activations Density 0.024%

    No Known Activations