© 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. 14633
    Prev
    Next
    INDEX
    Explanations

    approaching danger

    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
    åģ¶
    -0.24
     spot
    -0.20
    失
    -0.20
    spot
    -0.20
    Spot
    -0.20
    åģ¶å°Ķ
    -0.19
    .tap
    -0.19
    åģļè¿ĩ
    -0.18
    ç¿İ
    -0.18
    ury
    -0.18
    POSITIVE LOGITS
     danger
    0.23
    éĢ¼è¿ij
    0.23
    åĪ°æĿ¥
    0.23
    åį±éĻ©
    0.22
    è¶ĭåĬ¿
    0.21
    åĬ¿å¤´
    0.21
     imminent
    0.20
     toward
    0.20
    åľ°éĿ¢
    0.20
    гоÑĤов
    0.20
    Activations Density 0.034%

    No Known Activations