© 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. 29307
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ÙħاÙĨ
    -0.08
     ΣÏį
    -0.07
    .Sdk
    -0.07
    ABL
    -0.07
    Ñģле
    -0.07
    entered
    -0.07
    çŁ¥
    -0.07
    acher
    -0.07
    åĢ¾
    -0.07
    -runtime
    -0.07
    POSITIVE LOGITS
    åĴĮè°IJçļĦ
    0.07
    äºīåħī
    0.07
    亲亲
    0.07
    æĶ¾çŁ¢
    0.07
    áºŃt
    0.07
    Ợ
    0.07
    ievo
    0.06
    ussin
    0.06
    ieee
    0.06
    éĵ¶çīĮ
    0.06
    Activations Density 0.000%

    No Known Activations