© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 19085
    Prev
    Next
    INDEX
    Explanations

    explaining how or why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºĨä½łçļĦ
    -0.07
    /from
    -0.07
    ungle
    -0.07
    olume
    -0.07
    azar
    -0.06
    acks
    -0.06
    ä½łåij¢
    -0.06
    gmt
    -0.06
    以ä¸ĭæĿ¡ä»¶
    -0.06
    tage
    -0.06
    POSITIVE LOGITS
     how
    0.13
     why
    0.13
    å¦Ĥä½ķéĢļè¿ĩ
    0.12
    为ä»Ģä¹Ī
    0.11
    why
    0.11
    为ä½ķ
    0.11
    å¦Ĥä½ķåľ¨
    0.10
    how
    0.10
    ä»Ģä¹Īæĺ¯
    0.10
    å¦Ĥä½ķçĶ¨
    0.10
    Activations Density 0.051%

    No Known Activations