© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25144
    Prev
    Next
    INDEX
    Explanations

    sequence of numbers and letters

    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
    æ
    -0.07
    ROID
    -0.07
    ãĤ«ãĥ©
    -0.07
    oir
    -0.06
    èIJ½æĹ¥
    -0.06
     colloc
    -0.06
    ÃīN
    -0.06
    _FUNCTION
    -0.06
    ç²ķ
    -0.06
    ahu
    -0.06
    POSITIVE LOGITS
    åºıåĪĹ
    0.08
     followed
    0.08
    åħ¬çĶ¨
    0.08
    ambul
    0.08
    çļĦ大éĩı
    0.08
    izoph
    0.07
    Ñģени
    0.07
    :hidden
    0.07
    auga
    0.07
    串
    0.07
    Activations Density 0.014%

    No Known Activations