© 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. 50371
    Prev
    Next
    INDEX
    Explanations

    .blogspot

    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
    amenta
    -0.08
    è¿ħ鼷
    -0.07
    orman
    -0.07
    åĴĮæĶ¿åºľ
    -0.07
    cpt
    -0.07
    åİŁä½ĵ
    -0.07
    IZER
    -0.07
    ĻĤ
    -0.07
    ä¿¡æģ¯æŁ¥è¯¢
    -0.07
    éħ
    -0.07
    POSITIVE LOGITS
    ืà¹īà¸Ń
    0.07
    ç¦
    0.06
    ä¸ī代
    0.06
    chr
    0.06
    ãĢħãģ«
    0.06
    ãĢħ
    0.06
    __/
    0.06
    ...).
    0.06
    Æ¡
    0.06
    åIJĥäºı
    0.06
    Activations Density 0.008%

    No Known Activations