© 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. 14079
    Prev
    Next
    INDEX
    Explanations

    Datek Online, Tottori, IHA, AUC, KLM, ToolBar, stellenwerk, King County

    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
    çĶļèĩ³æĺ¯
    -0.23
    ven
    -0.21
    ved
    -0.20
     ven
    -0.19
    Ven
    -0.18
    çĤ¼
    -0.18
    ab
    -0.18
    dna
    -0.18
    uf
    -0.17
    çĶļèĩ³
    -0.17
    POSITIVE LOGITS
    ç»ĩ
    0.23
    ÙĬÙĨا
    0.20
    [mask
    0.19
    기ê´Ģ
    0.18
    èĵij
    0.18
    åıijåŀĭ
    0.18
    _NEED
    0.18
    åıijè¨Ģ人
    0.18
    ä¸įæĩĤ
    0.18
    缮çļĦåľ¨äºİ
    0.17
    Activations Density 0.038%

    No Known Activations