© 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. 64637
    Prev
    Next
    INDEX
    Explanations

    EXPECT followed by true or false

    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
    arit
    -0.08
    sters
    -0.08
    usercontent
    -0.08
    /www
    -0.07
    æĸ°éĹ»å®¢æĪ·ç«¯
    -0.07
    chino
    -0.07
    å¤ļå¾Ĺ
    -0.07
    quila
    -0.07
    chau
    -0.07
    ihad
    -0.07
    POSITIVE LOGITS
    rof
    0.06
    kel
    0.06
    abolic
    0.06
    f
    0.06
    wing
    0.06
    åĪĨ管
    0.06
     Rav
    0.06
     mơ
    0.06
    é¦
    0.06
    æĸĩéĽĨ
    0.05
    Activations Density 0.001%

    No Known Activations