© 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. 2426
    Prev
    Next
    INDEX
    Explanations

    invitations

    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
    boy
    -0.24
    hiba
    -0.21
    羸
    -0.20
    curity
    -0.20
    bon
    -0.20
    eder
    -0.19
    åı¯æĢľ
    -0.19
    much
    -0.19
    .Buttons
    -0.19
    åĶ¯ä¸Ģ
    -0.18
    POSITIVE LOGITS
    ersed
    0.23
     souls
    0.23
    äºĨ解ä¸Ģä¸ĭ
    0.21
     readers
    0.20
    underline
    0.20
    åĴĮæĶ¯æĮģ
    0.19
     scrutiny
    0.19
    读èĢħ
    0.19
     upon
    0.19
     collaboration
    0.19
    Activations Density 0.013%

    No Known Activations