© 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. 26163
    Prev
    Next
    INDEX
    Explanations

    ratio or comparison

    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
    _ADAPTER
    -0.08
    erton
    -0.07
    utas
    -0.07
    åĴĮåįİ
    -0.07
    throp
    -0.07
    æĿ¥è¡¨è¾¾
    -0.07
    olina
    -0.07
    ä¸įæľį
    -0.06
    çī¹å°Ķ
    -0.06
     compliment
    -0.06
    POSITIVE LOGITS
    çĽ¸å¯¹äºİ
    0.09
    缸è¾ĥäºİ
    0.09
    ëij¥
    0.08
    缸æ¯Ķäºİ
    0.08
    erer
    0.08
    bus
    0.07
    upes
    0.07
    æ¯Ķèµ·
    0.07
    akis
    0.07
    ä¹Łæ¯Ķ
    0.07
    Activations Density 0.242%

    No Known Activations