© 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. 41870
    Prev
    Next
    INDEX
    Explanations

    DLBCL, TPU, PF, VEGF, NLDO

    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
    esson
    -0.07
    essen
    -0.07
     poc
    -0.06
    æľ¬ä¼ģä¸ļ
    -0.06
    inov
    -0.06
    umba
    -0.06
    awa
    -0.06
    äºĶåĪĨ
    -0.06
    oy
    -0.06
    awas
    -0.06
    POSITIVE LOGITS
    utati
    0.07
     xô
    0.07
     Sor
    0.07
    对çĹĩä¸ĭèį¯
    0.07
    æĶ¾åģĩ
    0.06
    ·¸
    0.06
    åĩĨå¤ĩ好äºĨåIJĹ
    0.06
    馨
    0.06
    chini
    0.06
    ixel
    0.06
    Activations Density 0.038%

    No Known Activations