© 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. 13882
    Prev
    Next
    INDEX
    Explanations

    folate, follicular, folio

    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
    ãģªãĤīãģªãģĦ
    -0.19
    ingly
    -0.19
    ened
    -0.17
    oline
    -0.16
    LIN
    -0.16
    Ãłng
    -0.15
    åIJĦæł·
    -0.15
    便æį·
    -0.15
    liness
    -0.15
    er
    -0.15
    POSITIVE LOGITS
    aires
    0.19
    ìķ¼
    0.16
    uration
    0.16
    orent
    0.15
    icious
    0.15
     inmate
    0.15
    ãģ°
    0.15
     eens
    0.15
    irsch
    0.14
    éľ²å¤©
    0.14
    Activations Density 0.011%

    No Known Activations