© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1596
    Prev
    Next
    INDEX
    Explanations

    method signatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    индивид
    -0.73
    artisanlib
    -0.66
    индив
    -0.65
    медиÑĨинÑģк
    -0.64
    ÑĢеги
    -0.63
    spNet
    -0.63
    :UIControl
    -0.62
    apgolly
    -0.61
    sÅĤaw
    -0.61
    mPid
    -0.59
    POSITIVE LOGITS
    already
    0.44
    Need
    0.42
    needs
    0.42
    mandatory
    0.42
    points
    0.41
    your
    0.41
    really
    0.41
    minimum
    0.41
    ignore
    0.40
    Final
    0.40
    Activations Density 1.597%

    No Known Activations