© 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. 16424
    Prev
    Next
    INDEX
    Explanations

    lottery or land parcel

    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
    çĸļ
    -0.19
    hoot
    -0.17
    çįł
    -0.17
    /up
    -0.17
    _LVL
    -0.16
    elems
    -0.16
    eus
    -0.15
    åIJijãģį
    -0.15
    lection
    -0.15
    gent
    -0.14
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.29
    ting
    0.28
    tery
    0.23
    ter
    0.23
    imes
    0.19
    kinson
    0.19
    ss
    0.18
    issement
    0.17
    ween
    0.17
    size
    0.16
    Activations Density 0.013%

    No Known Activations