© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12534
    Prev
    Next
    INDEX
    Explanations

    discharge records, franchise tag, protein kinase, knot homology

    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
    apses
    -0.22
    éĥ¨åī¯éĥ¨éķ¿
    -0.21
    baugh
    -0.21
    wers
    -0.19
    åŃIJéĩĮ
    -0.18
    æīĢåģļçļĦ
    -0.18
    -fields
    -0.18
    -0.18
    amus
    -0.18
    åħ·ä½ĵæĥħåĨµ
    -0.18
    POSITIVE LOGITS
    èĪĴå¿ĥ
    0.20
    scoped
    0.19
    è®©æĽ´å¤ļ
    0.19
     darn
    0.18
    _PICTURE
    0.18
    åĸĨ
    0.18
    bild
    0.17
    ìĥģ
    0.17
    damn
    0.17
    æĺ¯ä»İ
    0.17
    Activations Density 0.737%

    No Known Activations