© 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. 14101
    Prev
    Next
    INDEX
    Explanations

    diff, gli, A, an, ADHD, rest, file, list, ad, gases

    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
    èĢĥè¯ķçļĦ
    -0.07
    ultz
    -0.07
    WindowSize
    -0.07
    ffe
    -0.07
    å¤ļç±³
    -0.07
    ä¸Ģåīij
    -0.06
     quint
    -0.06
    XHR
    -0.06
    lops
    -0.06
    æī¹åĩĨçļĦé¡¹çĽ®
    -0.06
    POSITIVE LOGITS
    æĮĤ
    0.08
    ç´Ģ
    0.07
    æİĽ
    0.07
    ضÙĬ
    0.07
    æľį
    0.07
    天å®ī
    0.07
    纪
    0.07
     rzecz
    0.06
    è¢
    0.06
    urn
    0.06
    Activations Density 0.548%

    No Known Activations