© 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. 56480
    Prev
    Next
    INDEX
    Explanations

    stages of progression

    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
    Fetcher
    -0.08
    çĭ¬æłijä¸Ģå¸ľ
    -0.08
    ä¸Ĭä¸ĭ
    -0.08
    æĶ¶èĹıæľ¬ç«Ļ
    -0.08
    æį¢æīĭ
    -0.07
    oldt
    -0.07
    quet
    -0.07
    اتÙĬ
    -0.07
    为èį£
    -0.07
    oes
    -0.07
    POSITIVE LOGITS
     progressively
    0.14
    éĢIJæŃ¥
    0.12
     gradually
    0.11
     dần
    0.11
    å±Ĥå±Ĥ
    0.11
     layers
    0.10
    —from
    0.10
     graduated
    0.09
    éĢĴ
    0.09
    æ¸IJè¿Ľ
    0.09
    Activations Density 0.067%

    No Known Activations