© 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. 62449
    Prev
    Next
    INDEX
    Explanations

    copyright or license

    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
    istic
    -0.08
    hood
    -0.08
    Ø©
    -0.08
    ------------
    -0.07
    Ø¡
    -0.07
    ings
    -0.07
    ä¸įæĭĶ
    -0.07
    re
    -0.06
    ls
    -0.06
    enge
    -0.06
    POSITIVE LOGITS
    ummings
    0.15
    opyright
    0.14
    LOUD
    0.14
    leanup
    0.13
    rawler
    0.13
    leared
    0.13
    ognito
    0.13
    emetery
    0.13
    astle
    0.13
    Åĵur
    0.13
    Activations Density 1.855%

    No Known Activations