© 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. 25852
    Prev
    Next
    INDEX
    Explanations

    bladder cancer and lesions

    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
    ç±
    -0.08
    åħ½
    -0.07
    angka
    -0.07
    æķij人
    -0.07
     conserv
    -0.07
    èĦĬæ¤İ
    -0.07
     jal
    -0.07
    è¿IJç®Ĺ
    -0.07
    大è±Ĩ
    -0.07
    å¥ĹåĪ©
    -0.07
    POSITIVE LOGITS
    é»ıèĨľ
    0.12
    ç²ĺèĨľ
    0.12
     ÑģлизиÑģÑĤой
    0.11
    ç³ľçĥĤ
    0.11
     muc
    0.10
     epith
    0.10
     niêm
    0.09
    å£ģä¸Ĭ
    0.09
     ulcer
    0.08
    æģ¯èĤī
    0.08
    Activations Density 0.239%

    No Known Activations