© 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. 61316
    Prev
    Next
    INDEX
    Explanations

    characteristic pattern

    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
    ä¸įæĺİçĻ½
    -0.07
    loth
    -0.06
    å¦Ĥæŀľæĺ¯
    -0.06
    ovsky
    -0.06
     '
    -0.06
    ä¸įæ¸ħæ¥ļ
    -0.06
    aland
    -0.06
    iki
    -0.05
     Tand
    -0.05
    POSE
    -0.05
    POSITIVE LOGITS
    enj
    0.08
    @click
    0.08
    .serv
    0.08
    åĨ²åĩº
    0.08
    nty
    0.08
    cpt
    0.07
    并使
    0.07
    éŨåħ³
    0.07
    表çݰ为
    0.07
    orgh
    0.07
    Activations Density 0.087%

    No Known Activations