© 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. 58226
    Prev
    Next
    INDEX
    Explanations

    isomorphic to, via embeddings

    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
    stad
    -0.08
    ossal
    -0.07
    éĴĪ对
    -0.07
    éĴĪ对ä¸įåIJĮ
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.07
    kle
    -0.07
    对äºİè¿ĻäºĽ
    -0.07
    åīĬ
    -0.07
    å°½
    -0.07
     dispro
    -0.07
    POSITIVE LOGITS
     via
    0.10
    via
    0.09
     Via
    0.09
    å¤§åľ°
    0.08
    Via
    0.08
    èĩªçĦ¶åľ°
    0.08
    _plugins
    0.08
    orto
    0.07
    _via
    0.07
    _projection
    0.07
    Activations Density 0.017%

    No Known Activations