© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 459
    Prev
    Next
    INDEX
    Explanations

    ethnic groups, locations, specific contexts

    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
    <fieldset
    -0.23
    ..."
    -0.22
     Alley
    -0.22
    aney
    -0.21
    _cpp
    -0.21
    blo
    -0.21
    sty
    -0.21
     Schro
    -0.21
    etur
    -0.20
    èľķ
    -0.20
    POSITIVE LOGITS
    à°³
    0.24
    éķŃ
    0.24
    bidden
    0.24
     REP
    0.23
    åIJĥäºı
    0.23
    apons
    0.23
     forgiving
    0.23
     kald
    0.23
    apan
    0.23
    REP
    0.22
    Activations Density 0.507%

    No Known Activations