© 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. 16580
    Prev
    Next
    INDEX
    Explanations

    business publications

    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
    tier
    -0.20
    _STMT
    -0.19
    ·»
    -0.19
    æĬµ
    -0.19
    ingleton
    -0.18
    ated
    -0.18
    滥
    -0.18
    yen
    -0.18
    atorial
    -0.17
    äºĤ
    -0.17
    POSITIVE LOGITS
     Tud
    0.20
     apple
    0.19
    oks
    0.19
    place
    0.19
    åİŁåŀĭ
    0.19
    çł´äº§
    0.18
    强è¡Į
    0.18
    éŀħ
    0.18
    mount
    0.18
    æħ
    0.18
    Activations Density 0.002%

    No Known Activations