© 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. 11120
    Prev
    Next
    INDEX
    Explanations

    travel across countries or world

    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
    èĦĤ
    -0.23
    çķ´
    -0.22
    furt
    -0.20
    amel
    -0.19
    usher
    -0.19
    æĽ´å¤ļä¿¡æģ¯
    -0.19
    â¾Ľ
    -0.19
    LOTS
    -0.19
    åľ¨å¤ĸ
    -0.19
    bish
    -0.18
    POSITIVE LOGITS
    å®Įæķ´çļĦ
    0.23
    å½ĵæĪIJ
    0.21
    次æķ°
    0.21
    å¾ģæľį
    0.21
    å®ĮæĪIJ
    0.21
    complete
    0.20
    èĢĹ
    0.20
    æĮijæĪĺ
    0.20
    å®Įæķ´
    0.20
    challenge
    0.19
    Activations Density 0.021%

    No Known Activations