© 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. 10831
    Prev
    Next
    INDEX
    Explanations

    Webster or Burke

    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
    baugh
    -0.18
    ocks
    -0.17
    itud
    -0.17
    éļĻ
    -0.17
    _UNS
    -0.16
    èĢ¶
    -0.16
    _pv
    -0.16
    æµ£
    -0.16
    spe
    -0.16
    ìį¨
    -0.16
    POSITIVE LOGITS
    ä¹ĭå¤ľ
    0.18
    uir
    0.17
    дан
    0.16
    less
    0.16
    åľ¨æ·±åľ³
    0.16
    pace
    0.15
    enstein
    0.15
    ·
    0.15
    ench
    0.15
     biçim
    0.15
    Activations Density 0.002%

    No Known Activations