© 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. 15779
    Prev
    Next
    INDEX
    Explanations

    omni, ubiquitous

    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
    ä»Ķ
    -0.17
    leton
    -0.17
    compact
    -0.17
    ìļ°
    -0.17
    erek
    -0.17
    åľ°æ®µ
    -0.17
    wards
    -0.16
    ERN
    -0.16
    سر
    -0.16
    NR
    -0.16
    POSITIVE LOGITS
    ç¼¥
    0.20
    çŁ¥æĻĵ
    0.18
     piss
    0.18
    еÑģÑĤво
    0.18
    ymous
    0.18
    _except
    0.18
    涯
    0.17
    erta
    0.17
    ä¸ĩçī©
    0.16
    è§īå¾Ĺå¾Ī
    0.16
    Activations Density 0.016%

    No Known Activations