© 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. 10817
    Prev
    Next
    INDEX
    Explanations

    parenthetical emphasis or exclamation

    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
    è§ŀ
    -0.21
    Certainly
    -0.20
    ç¥Ģ
    -0.19
    unker
    -0.19
    Known
    -0.18
    佬
    -0.18
    éĢļè¡Į
    -0.18
    è¾ĥå¿«
    -0.18
    åĺ²
    -0.18
     paraph
    -0.18
    POSITIVE LOGITS
    å±ħçĦ¶
    0.28
    ç«ŁçĦ¶
    0.28
    ç«Ł
    0.23
    èĢĮä¸Ķ
    0.23
    !)
    0.22
    ãģĹãģĭãĤĤ
    0.22
    AMA
    0.21
    ï¼ģ
    0.21
    (!
    0.21
    !,
    0.20
    Activations Density 0.065%

    No Known Activations