© 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. 15835
    Prev
    Next
    INDEX
    Explanations

    pomegranates, illustrated, Telerik, Mediterranean, Related, New, Q

    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
     ratt
    -0.19
    åĵº
    -0.19
     mã
    -0.18
    åīįéĢĶ
    -0.18
    Trader
    -0.18
    resize
    -0.17
    èķĪ
    -0.17
    åįł
    -0.17
    ogen
    -0.17
    ograms
    -0.17
    POSITIVE LOGITS
    /red
    0.20
    çī¹éĤĢ
    0.20
    çłĢ
    0.19
    çŁ³æ¦´
    0.19
    _FATAL
    0.18
    å¹²
    0.17
    uby
    0.17
     беÑĢем
    0.16
    èĭ·
    0.16
     Yan
    0.16
    Activations Density 0.001%

    No Known Activations