© 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. 18636
    Prev
    Next
    INDEX
    Explanations

    word list explanation

    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
    <|fim_prefix|>
    -0.09
    áb
    -0.09
    对ä¸Ĭè¿°
    -0.08
    bia
    -0.08
    uton
    -0.08
    utom
    -0.08
    éĢļè¿ĩ以ä¸Ĭ
    -0.08
    æĥĬ人çļĦ
    -0.08
    æľ¬ç«ĻåĨħ容
    -0.08
    otos
    -0.08
    POSITIVE LOGITS
    pk
    0.06
    âĢ
    0.06
    ç¬
    0.06
    以ä¸ĭæĺ¯å°ıç¼ĸ
    0.06
    éĸ
    0.06
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.06
    ãĢİ
    0.06
     likely
    0.06
    å¬
    0.06
    aman
    0.05
    Activations Density 0.024%

    No Known Activations