© 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. 14600
    Prev
    Next
    INDEX
    Explanations

    bacterial isolation

    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
    дÑĥÑĤ
    -0.20
    æĿ¥åĽŀ
    -0.19
    ->__
    -0.19
     metaphor
    -0.18
    ä½Ľæ³ķ
    -0.18
     Superv
    -0.18
     plur
    -0.18
     fucking
    -0.18
    ëĭ¬
    -0.18
    vtk
    -0.18
    POSITIVE LOGITS
    èĮ´
    0.22
    æ¸ł
    0.21
    è´¨éĩıå®īåħ¨
    0.20
     Osman
    0.20
    çļĦçĥŃæĥħ
    0.20
     tuy
    0.20
     honorary
    0.19
    agini
    0.19
    辫
    0.19
    CORD
    0.19
    Activations Density 0.643%

    No Known Activations