© 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. 13347
    Prev
    Next
    INDEX
    Explanations

    bribery or ransom

    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
    girls
    -0.20
    æĽ·
    -0.18
    kir
    -0.18
    tör
    -0.18
    krit
    -0.17
    éľģ
    -0.17
    obar
    -0.17
    wards
    -0.17
    æ°¦
    -0.17
    ยว
    -0.17
    POSITIVE LOGITS
    èµĤ
    0.23
    wort
    0.18
     compass
    0.18
    anke
    0.17
    /mock
    0.17
    inal
    0.16
    bery
    0.16
     beacon
    0.16
    inel
    0.16
    çŀĴ
    0.16
    Activations Density 0.005%

    No Known Activations