© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12345
    Prev
    Next
    INDEX
    Explanations

    surviving

    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
    .assertIsNot
    -0.19
    åIJĦè¡Į
    -0.17
    _GUID
    -0.17
    Ur
    -0.17
    _Construct
    -0.17
    没éĹ®é¢ĺ
    -0.17
    æ¼ł
    -0.17
    rement
    -0.17
    æµģåĩº
    -0.17
    åIJĦçľģ
    -0.16
    POSITIVE LOGITS
    ington
    0.20
     Colomb
    0.20
    ecess
    0.20
    ç¥ī
    0.20
    äºĨåĩł
    0.19
    èįª
    0.19
    亲å±ŀ
    0.19
    aped
    0.18
    iscal
    0.18
    elda
    0.18
    Activations Density 0.002%

    No Known Activations