© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33216
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    <|box_end|>
    -0.09
    queur
    -0.09
    æļ§
    -0.07
    Ä°L
    -0.07
    æĻļæĬ¥
    -0.07
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    åı¯æĺ¯æĪij
    -0.07
    ë
    -0.07
    pring
    -0.07
    æ¯Ķå¦Ĥ说
    -0.07
    POSITIVE LOGITS
    Cle
    0.07
    åī¥
    0.07
    æıIJéĨĴä½ł
    0.06
     Cle
    0.06
    éĩĩ
    0.06
     Ehren
    0.06
     dich
    0.06
     Dich
    0.06
    rit
    0.06
    hel
    0.06
    Activations Density 0.003%

    No Known Activations