© 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. 1611
    Prev
    Next
    INDEX
    Explanations

    javascript syntax, closing braces

    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
     Comet
    -0.21
     Sco
    -0.20
     Imm
    -0.20
     exp
    -0.20
    _sibling
    -0.20
    _then
    -0.20
    æ³
    -0.20
     exper
    -0.20
     Tales
    -0.20
     (),
    -0.19
    POSITIVE LOGITS
    itti
    0.24
    unn
    0.24
    åĶĽ
    0.23
    MER
    0.22
    haul
    0.22
    Ups
    0.22
    mill
    0.21
    çīĪæĿĥå½Ĵ
    0.21
    æѤå¤ĸ
    0.21
    var
    0.21
    Activations Density 0.602%

    No Known Activations