© 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. 11436
    Prev
    Next
    INDEX
    Explanations

    vegetables

    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
    ãģ£ãģįãĤĬ
    -0.23
    ned
    -0.22
    åĽŀäºĭ
    -0.20
    åħ±æĮ¯
    -0.17
    itt
    -0.17
    raid
    -0.16
    ormal
    -0.16
    ç²¾åĬĽ
    -0.15
    (equal
    -0.15
    itory
    -0.15
    POSITIVE LOGITS
    大æ£ļ
    0.20
    stalk
    0.20
    endor
    0.19
    åĽŃ
    0.19
    stype
    0.17
    ALLY
    0.17
    sWith
    0.17
    é½IJåħ¨
    0.16
    ENDOR
    0.16
    ebra
    0.16
    Activations Density 0.008%

    No Known Activations