© 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. 2516
    Prev
    Next
    INDEX
    Explanations

    Copyright ©

    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
    InputModule
    -0.23
     grids
    -0.21
    GRID
    -0.21
    ijľ
    -0.21
     weaving
    -0.21
    ẫ
    -0.21
    ä¸ĭ次
    -0.21
    bek
    -0.21
    çļĦæĥħæĦŁ
    -0.21
    泫
    -0.21
    POSITIVE LOGITS
    失踪
    0.26
     Circus
    0.23
     objection
    0.23
    循
    0.23
     **
    0.22
    欺
    0.22
     firewall
    0.22
    ÙĬز
    0.21
    anime
    0.21
    tel
    0.21
    Activations Density 0.002%

    No Known Activations