© 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. 15454
    Prev
    Next
    INDEX
    Explanations

    place names and entities

    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
     cel
    -0.21
     internal
    -0.20
    ä¸Ģæĸ¹éĿ¢
    -0.20
    æģ©
    -0.18
    _again
    -0.17
    NX
    -0.17
     lap
    -0.17
    Ñĥма
    -0.17
    aison
    -0.17
    åıĪè¦ģ
    -0.17
    POSITIVE LOGITS
    å¡ij
    0.23
    便æ°ij
    0.20
    åĶ¯ä¸ĢçļĦ
    0.20
    èĤĭ
    0.20
    å¨ģå°Ķ
    0.19
    ateria
    0.19
    .variant
    0.19
    åĶ¯ä¸Ģ
    0.19
    åİĦ
    0.19
    coverage
    0.19
    Activations Density 0.130%

    No Known Activations