© 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. 12815
    Prev
    Next
    INDEX
    Explanations

    magnificent, gorgeous descriptions

    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
    å¯¹æľªæĿ¥
    -0.18
    æĭ¯
    -0.18
    usch
    -0.18
    èĻij
    -0.18
    éĩįè¦ģæĦıä¹ī
    -0.18
    idian
    -0.18
    åıĭ好
    -0.18
    itat
    -0.17
    âĢ¢↵↵
    -0.17
    ention
    -0.16
    POSITIVE LOGITS
    LY
    0.22
    -looking
    0.21
    ly
    0.20
    liest
    0.19
    ration
    0.19
    его
    0.18
     vistas
    0.18
    nature
    0.18
    åłµ
    0.17
    ible
    0.16
    Activations Density 0.006%

    No Known Activations