© 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. 3071
    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
    æĢ»ä½ĵä¸Ĭ
    -0.07
    iar
    -0.07
    ar
    -0.07
    Äı
    -0.07
    éĢł
    -0.07
    ç³»
    -0.07
    å®ŀéĻħéľĢæ±Ĥ
    -0.06
    iat
    -0.06
    çľ
    -0.06
    arr
    -0.06
    POSITIVE LOGITS
    raud
    0.09
    комо
    0.08
    rase
    0.08
    æľ¬å¸ĸ
    0.07
    avez
    0.07
    ROID
    0.07
    _COUNTER
    0.07
    kopf
    0.07
    gris
    0.07
    ä¿ĿèŃī
    0.07
    Activations Density 0.000%

    No Known Activations