© 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. 11383
    Prev
    Next
    INDEX
    Explanations

    Enabled capability, credit card information

    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
    lesh
    -0.25
    indh
    -0.21
    ÑģоÑĢ
    -0.19
    导åIJij
    -0.19
     sơ
    -0.18
    åĩºåĵģ
    -0.18
    hest
    -0.18
    é¢ł
    -0.18
    ITO
    -0.18
    åĽ½åĨħå¤ĸ
    -0.18
    POSITIVE LOGITS
     bat
    0.19
     rad
    0.19
     Source
    0.19
     batting
    0.17
     Const
    0.17
     Lore
    0.17
    iếc
    0.17
    yahoo
    0.17
    ches
    0.17
     Q
    0.16
    Activations Density 1.122%

    No Known Activations