© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 60547
    Prev
    Next
    INDEX
    Explanations

    CD31Bright, CD34+, CD45-/Dim

    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
    /loading
    -0.07
    ?type
    -0.07
    ÑĤÑĢеÑĤÑĮ
    -0.06
    èĩªæĿ¥
    -0.06
    igre
    -0.06
    noticed
    -0.06
     gir
    -0.06
    ì¡°
    -0.06
    cion
    -0.06
    å͝
    -0.06
    POSITIVE LOGITS
    ebin
    0.08
    æīĢæ¬²
    0.07
    utr
    0.07
    çīł
    0.07
    çĻ¾åº¦äºij
    0.07
    HTTPRequest
    0.07
    ä¹ĭå¤ļ
    0.07
    çϾå§ĵç½ij
    0.07
    ·¸
    0.07
     mươi
    0.07
    Activations Density 0.019%

    No Known Activations