© 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. 14917
    Prev
    Next
    INDEX
    Explanations

    this indicating context

    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
    æĬĵç´§
    -0.21
    entai
    -0.20
    åĪĽæĸ°èĥ½åĬĽ
    -0.19
    bez
    -0.19
    éĢĤåIJĪèĩªå·±
    -0.19
    åĿIJåľ¨
    -0.19
    èĬŁ
    -0.18
     dy
    -0.18
    家éĥ½çŁ¥éģĵ
    -0.18
    åĬĪ
    -0.18
    POSITIVE LOGITS
    å±ķ示
    0.20
     liá»ĩt
    0.19
    å¥ķ
    0.19
    oha
    0.19
    æīĢæıIJä¾ĽçļĦ
    0.18
     facil
    0.18
    urate
    0.18
    ä¸į便
    0.18
    exact
    0.18
    ãĥıãĤ¦
    0.18
    Activations Density 0.150%

    No Known Activations