© 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. 14694
    Prev
    Next
    INDEX
    Explanations

    somewhere nowhere anywhere

    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
    ãģĵãģ¨ãģĮãģĤãĤĭ
    -0.18
    spy
    -0.18
    åĢĶ
    -0.18
    åı¦ä¸Ģç§į
    -0.18
    reet
    -0.17
    æĥķ
    -0.17
    弩
    -0.17
    ç³ľ
    -0.17
    sWith
    -0.16
    ãģĵãģ¨ãģ«
    -0.16
    POSITIVE LOGITS
    abouts
    0.28
    upon
    0.22
     else
    0.22
    人士
    0.21
    else
    0.19
    ever
    0.18
    kick
    0.18
    Else
    0.18
    hin
    0.17
    _else
    0.17
    Activations Density 0.013%

    No Known Activations