© 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. 16287
    Prev
    Next
    INDEX
    Explanations

    'omics technologies

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.18
    /or
    -0.18
    妨
    -0.18
    UIS
    -0.17
    _pull
    -0.16
    rops
    -0.16
    ä¸ĵä¸ļ人士
    -0.16
    å°±æĿ¥çľĭçľĭ
    -0.16
    ugs
    -0.15
    å¡ŀ
    -0.15
    POSITIVE LOGITS
    ãĢģ“
    0.20
    ÂĢÂĻ
    0.18
    ำ
    0.18
    äºĭåĦ¿
    0.17
    chia
    0.17
    _:*
    0.16
    /-
    0.16
    FilterWhere
    0.16
    SplitOptions
    0.16
    oord
    0.15
    Activations Density 0.021%

    No Known Activations