© 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. 16688
    Prev
    Next
    INDEX
    Explanations

    son-in-law

    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
     transf
    -0.20
    åĦĺ
    -0.18
    _parsed
    -0.18
    лаг
    -0.18
    éľĸ
    -0.18
    åĹľ
    -0.17
    /sc
    -0.17
    luent
    -0.17
     Barth
    -0.17
    otions
    -0.17
    POSITIVE LOGITS
    eger
    0.23
    éĻ¶
    0.19
     halls
    0.18
    çªĪ
    0.18
    滥
    0.18
     Avery
    0.18
    Generic
    0.18
    豺
    0.17
    åıįè¿ĩæĿ¥
    0.17
    对èĩªå·±
    0.17
    Activations Density 0.002%

    No Known Activations