© 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. 16869
    Prev
    Next
    INDEX
    Explanations

    writing about interests and experiences

    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
    ä½ķåĨµ
    -0.23
    íĹĢ
    -0.22
    UAGE
    -0.22
    alach
    -0.21
    çĮĽçĦ¶
    -0.21
    ãĤŃãĥ£ãĥ³ãĥļ
    -0.21
    kening
    -0.20
    ä»ĬæĻļ
    -0.20
    åIJĵå¾Ĺ
    -0.20
    æĻļé¥Ń
    -0.20
    POSITIVE LOGITS
     life
    0.23
    åĬĽæ±Ĥ
    0.21
    å¸ĮæľĽéĢļè¿ĩ
    0.20
     spare
    0.20
    :-
    0.19
     ÑĤо
    0.19
    (d
    0.19
    (
    0.19
     weird
    0.19
    Currently
    0.18
    Activations Density 0.146%

    No Known Activations