© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15795
    Prev
    Next
    INDEX
    Explanations

    species names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    åijĹ
    -0.22
    æµģ浪
    -0.21
    sphere
    -0.21
     converted
    -0.20
     converter
    -0.20
     conversion
    -0.20
    趸
    -0.20
    FAIL
    -0.20
    éĸĴ
    -0.19
    人å±ħ
    -0.19
    POSITIVE LOGITS
    moid
    0.23
    认åı¯
    0.21
     Pey
    0.20
    èĸ®
    0.20
    ROAD
    0.20
    åºĶæĶ¶
    0.20
    urus
    0.20
    ntax
    0.20
    -lnd
    0.19
    ç«ŀäºīåĬĽ
    0.19
    Activations Density 0.221%

    No Known Activations