© 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. 11603
    Prev
    Next
    INDEX
    Explanations

    how does

    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
    æĪ¿
    -0.20
    LED
    -0.20
    ial
    -0.20
    æĻ®
    -0.20
     Herc
    -0.20
    led
    -0.20
     deg
    -0.19
    æľ¬æĬ¥
    -0.18
     subsequent
    -0.18
    med
    -0.18
    POSITIVE LOGITS
    ç¼ķ
    0.21
    ç»ıéªĮåĴĮ
    0.20
    tör
    0.20
    /lists
    0.19
    æĪijä»¬ä¹Ł
    0.18
    åĮºåŁŁæĢ§
    0.18
    éĺħåİĨ
    0.18
    æ¾ľ
    0.18
    亲è¿ij
    0.18
    çĥŁåĽ±
    0.18
    Activations Density 0.019%

    No Known Activations