© 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. 56115
    Prev
    Next
    INDEX
    Explanations

    between, within, surrounded

    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
    éĩijæ¦ľ
    -0.08
    иÑģÑĤÑĢа
    -0.08
    æķĻè®Ń
    -0.08
    oslav
    -0.08
    subcategory
    -0.08
    çĶ¨æ³ķ
    -0.07
    ë¬ĺ
    -0.07
    æģ¯
    -0.07
    交æĺĵä¼ļ
    -0.07
     Burnett
    -0.07
    POSITIVE LOGITS
    rai
    0.07
    åħ¶å®ĥåªĴä½ĵ
    0.07
    iew
    0.07
     dashes
    0.07
    壽
    0.06
    æĻ¶æĻ¶
    0.06
    符
    0.06
     anl
    0.06
    ÑĢам
    0.06
    LD
    0.06
    Activations Density 0.001%

    No Known Activations