© 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. 13279
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    æ±²
    -0.23
    éĻĤ
    -0.21
    éĢļè¡Į
    -0.20
    rd
    -0.17
    .Expressions
    -0.17
    ucker
    -0.17
    elan
    -0.17
    æŀ³
    -0.16
    utz
    -0.16
    çķĶ
    -0.16
    POSITIVE LOGITS
    eenth
    0.44
    een
    0.23
    th
    0.18
    angers
    0.18
    éĩijå±±
    0.17
     thợ
    0.17
    驺
    0.17
    é¼»åŃIJ
    0.17
    人äºĭ
    0.17
    ãģĵãģ¨ãģ«
    0.17
    Activations Density 0.334%

    No Known Activations