© 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. 14417
    Prev
    Next
    INDEX
    Explanations

    Q: or Bank of

    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
    _DOC
    -0.21
    ç¯ĵ
    -0.21
    _TRY
    -0.20
    unar
    -0.20
     exert
    -0.20
     Panda
    -0.20
     Weiss
    -0.20
     Alto
    -0.19
     Piano
    -0.19
    _UNSIGNED
    -0.19
    POSITIVE LOGITS
    æĪĺæĸĹ
    0.27
    伤亡
    0.25
    æĪĺåľºä¸Ĭ
    0.25
    åĨ²éĶĭ
    0.23
    æĪĺæĸĹåĬĽ
    0.23
    å®ŀæĪĺ
    0.23
    æĪĺäºī
    0.23
    è§Ħ模
    0.22
    æĪĺ
    0.21
    ä¾Ľåħ»
    0.21
    Activations Density 0.016%

    No Known Activations