© 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. 56708
    Prev
    Next
    INDEX
    Explanations

    path or connectivity

    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
    ULER
    -0.08
    reh
    -0.08
    IQ
    -0.08
    zec
    -0.08
    hist
    -0.07
    çī©ä¸ļ管çIJĨæľīéĻIJåħ¬åı¸
    -0.07
    ило
    -0.07
    iq
    -0.07
    riger
    -0.07
     upright
    -0.07
    POSITIVE LOGITS
    abus
    0.08
     distances
    0.07
    åĴ«å°º
    0.07
     reachable
    0.07
     unreachable
    0.07
    对åIJĦ
    0.07
    广æĴŃ
    0.07
    磩éĺµ
    0.07
    éĢļè¾¾
    0.07
    对æīĢæľī
    0.07
    Activations Density 0.009%

    No Known Activations