© 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. 12096
    Prev
    Next
    INDEX
    Explanations

    skill level

    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
    еÑģÑĤи
    -0.21
    erving
    -0.20
    @@
    -0.20
    stag
    -0.19
    åħ¸
    -0.18
    obar
    -0.18
     préc
    -0.18
     Ñģов
    -0.18
    -net
    -0.18
    lob
    -0.18
    POSITIVE LOGITS
    级åĪ«
    0.28
    ãĥ¬ãĥĻãĥ«
    0.28
     level
    0.27
    级åĪ«çļĦ
    0.26
    çŃī级
    0.26
    ç¨ĭ度
    0.24
    _level
    0.23
     ÑĥÑĢовенÑĮ
    0.22
    驾é©Ń
    0.22
    Level
    0.21
    Activations Density 0.026%

    No Known Activations