© 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. 14398
    Prev
    Next
    INDEX
    Explanations

    gun violence, rules, control, trafficking

    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
    ij
    -0.17
    -vous
    -0.17
    angelo
    -0.16
    nce
    -0.16
    à¸Ńà¸ĩ
    -0.15
    andro
    -0.15
    icher
    -0.15
    ively
    -0.15
     nuances
    -0.15
    ughter
    -0.14
    POSITIVE LOGITS
    ning
    0.21
    ERIC
    0.20
    迹
    0.20
    zilla
    0.19
    lets
    0.19
    ned
    0.18
    manship
    0.18
    keepers
    0.18
    ILLA
    0.18
    ners
    0.18
    Activations Density 0.009%

    No Known Activations