© 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. 2483
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    ively
    -0.28
    uter
    -0.22
    itud
    -0.21
    -most
    -0.21
    ided
    -0.21
    uned
    -0.21
    ourd
    -0.21
    ihad
    -0.20
    OURNAL
    -0.20
    ÂŃing
    -0.20
    POSITIVE LOGITS
    æ¾ľ
    0.21
    管çIJĨå·¥ä½ľ
    0.21
    åħ¥å¢ĥ
    0.21
    transition
    0.21
    sites
    0.21
    er
    0.21
    ç»ıåİĨ
    0.20
    sphere
    0.20
    å¢ĥ
    0.20
    æ¦Ĩ
    0.20
    Activations Density 0.145%

    No Known Activations