© 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. 12801
    Prev
    Next
    INDEX
    Explanations

    Nash, stash, fetch, hash

    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
    ality
    -0.19
    ctime
    -0.19
    ctest
    -0.18
    isci
    -0.17
    èĨĬ
    -0.17
    uchar
    -0.17
    ÑĪка
    -0.17
    achel
    -0.16
    aits
    -0.16
    bern
    -0.16
    POSITIVE LOGITS
    es
    0.32
    s
    0.30
    ness
    0.25
    ings
    0.25
    able
    0.25
    rooms
    0.24
    mate
    0.24
    (es
    0.24
    inator
    0.23
    ingly
    0.23
    Activations Density 0.103%

    No Known Activations