© 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. 2532
    Prev
    Next
    INDEX
    Explanations

    weight loss or gain

    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
    æ´¾éģ£
    -0.28
    æī¼
    -0.26
     Powered
    -0.25
    åķ¼
    -0.25
    ponsored
    -0.25
     scramble
    -0.25
    Powered
    -0.24
     consort
    -0.23
    |[
    -0.23
     jointly
    -0.23
    POSITIVE LOGITS
     fluct
    0.31
    身é«ĺ
    0.31
    åĩıèĤ¥
    0.31
     plateau
    0.29
     inches
    0.29
    ä½ĵéĩį
    0.29
    _goal
    0.28
     recovery
    0.28
    ometer
    0.28
     peaked
    0.28
    Activations Density 0.019%

    No Known Activations