© 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. 12744
    Prev
    Next
    INDEX
    Explanations

    f/ or aperture

    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
     mor
    -0.20
    æĶĴ
    -0.18
    çļĦæŶéĹ´
    -0.18
    ç»ij
    -0.17
    æĿ¿åĿĹ
    -0.17
    ankan
    -0.17
    (material
    -0.17
     Burning
    -0.17
    .kotlin
    -0.16
    batim
    -0.16
    POSITIVE LOGITS
    å¾Ĺèµ·
    0.22
    æĶ¾å®½
    0.21
    å¾Īæ·±
    0.20
    bst
    0.19
    åı¤ä»Ĭ
    0.18
    ä¸Ģ举
    0.18
    éĢĨåĬ¿
    0.18
     INTERFACE
    0.18
    åIJĪä½ľåħ±èµ¢
    0.17
    _acl
    0.17
    Activations Density 0.004%

    No Known Activations