© 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. 11416
    Prev
    Next
    INDEX
    Explanations

    I followed by verbs

    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
    ens
    -0.20
    etre
    -0.20
    emb
    -0.20
    prim
    -0.20
    at
    -0.19
    oras
    -0.19
    aling
    -0.19
    Brandon
    -0.18
    ilan
    -0.18
    ym
    -0.18
    POSITIVE LOGITS
    è°ĥæݧ
    0.21
    æ²¹èħ»
    0.20
    éĵ±
    0.20
    èµ°åĩºæĿ¥
    0.20
    æ°Ķ温
    0.19
    èµ°è¿ĩ
    0.19
    å·¥ä½ľæĬ¥åijĬ
    0.19
    ä¸ŃåĽ½æĶ¿åºľ
    0.18
    è´«åĽ°äººåı£
    0.18
    ä½ľæ¡Ī
    0.18
    Activations Density 0.106%

    No Known Activations