© 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. 11193
    Prev
    Next
    INDEX
    Explanations

    latest, combined, the, download, car

    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
     зай
    -0.21
    åĽ¢åľĨ
    -0.20
    æĪ·åı£
    -0.19
    åĩºèµĦ
    -0.19
    å§ĭ建
    -0.19
    èī®
    -0.19
    å§ĭ
    -0.19
    ç¥ĸ
    -0.18
    å½ĵåľ°çļĦ
    -0.18
    æĻ®éĢļçļĦ
    -0.18
    POSITIVE LOGITS
     hot
    0.20
    çĥŃæĴŃ
    0.19
     Howell
    0.19
     binge
    0.19
    çĥŃçĤ¹
    0.19
     hottest
    0.19
    TERN
    0.19
    .jav
    0.18
    æ¯ıæĹ¥
    0.18
     empt
    0.18
    Activations Density 0.016%

    No Known Activations