© 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. 49543
    Prev
    Next
    INDEX
    Explanations

    measurement units (cm, inch, pt)

    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
    ersch
    -0.09
    hound
    -0.08
    stech
    -0.07
    codes
    -0.07
    Configurer
    -0.07
    Õ¡Õ°
    -0.07
    erschap
    -0.07
    orca
    -0.07
    rypt
    -0.07
    cwd
    -0.07
    POSITIVE LOGITS
    ëijIJ
    0.08
    ay
    0.07
    ëijIJê³ł
    0.07
    家常
    0.07
    åĴĮåIJĪä½ľ
    0.07
    sep
    0.07
    ully
    0.06
    Ø´ÙĨ
    0.06
    uch
    0.06
    ubi
    0.06
    Activations Density 0.002%

    No Known Activations