© 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. 16850
    Prev
    Next
    INDEX
    Explanations

    thin ultrabooks

    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
    AME
    -0.19
    tps
    -0.18
    ixin
    -0.17
    身ä½ĵåģ¥åº·
    -0.17
    onga
    -0.17
    ningen
    -0.17
    åĽºå®ļçļĦ
    -0.17
    agal
    -0.17
    uss
    -0.17
    resar
    -0.17
    POSITIVE LOGITS
     Concept
    0.25
    æ¦Ĥ念
    0.21
    们
    0.20
    è°±
    0.20
    çļĦæ¦Ĥ念
    0.20
    <![
    0.19
    纷纷
    0.19
    çIJĨ念
    0.19
    éĢ¸
    0.19
    anium
    0.18
    Activations Density 0.003%

    No Known Activations