© 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. 1520
    Prev
    Next
    INDEX
    Explanations

    overall, duplicate, single, companyname

    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
    .selector
    -0.27
    è¦ģ好好
    -0.23
    schedule
    -0.23
    selectors
    -0.23
    built
    -0.23
    .expect
    -0.22
    le
    -0.22
    zet
    -0.22
    Experiment
    -0.22
    çİĭçīĮ
    -0.22
    POSITIVE LOGITS
     Cancel
    0.24
    ÑĢеги
    0.23
     cancell
    0.22
     cancelled
    0.22
     collapse
    0.21
     *----------------------------------------------------------------
    0.21
    _void
    0.21
     cancel
    0.21
     cou
    0.21
     Either
    0.20
    Activations Density 0.001%

    No Known Activations