© 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. 44869
    Prev
    Next
    INDEX
    Explanations

    code assignment discussion

    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
     priz
    -0.07
    usel
    -0.07
    æľĿå¤ķ
    -0.07
    eya
    -0.07
    conom
    -0.07
    elyn
    -0.07
    ä¸įè°Ī
    -0.07
    éĢļå¸¸åľ¨
    -0.07
    pir
    -0.07
    nty
    -0.07
    POSITIVE LOGITS
    inna
    0.07
    cil
    0.07
    rific
    0.07
    æĮīè¦ģæ±Ĥ
    0.07
    æĥħ
    0.06
    inov
    0.06
    å®ĺæĸ¹
    0.06
    读èĢħ
    0.06
    -sync
    0.06
    çĹĽ
    0.06
    Activations Density 0.004%

    No Known Activations