© 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. 12907
    Prev
    Next
    INDEX
    Explanations

    burglary and related crimes

    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
    ccess
    -0.19
    thon
    -0.18
    .squareup
    -0.18
    stract
    -0.17
    ãģ£ãģįãĤĬ
    -0.17
    å¤ł
    -0.17
    tring
    -0.17
    esen
    -0.17
    xious
    -0.16
    çĹ£
    -0.15
    POSITIVE LOGITS
    OrUpdate
    0.18
    ivals
    0.16
    uen
    0.15
    হ
    0.15
    -minded
    0.15
    大æĸ¹
    0.14
    ãĥĥãĥĦ
    0.14
    åIJĦèĩª
    0.14
    iveness
    0.14
    gie
    0.14
    Activations Density 0.017%

    No Known Activations