© 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. 28030
    Prev
    Next
    INDEX
    Explanations

    `set` followed by `[` or `TZ` or `vendor`

    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
    对ä¸Ĭè¿°
    -0.08
    aż
    -0.08
    ushima
    -0.08
    gorith
    -0.07
    ovich
    -0.07
     foregoing
    -0.07
    å¼łå¤§
    -0.07
    izzie
    -0.07
    åĽ´çĿĢ
    -0.06
     aforementioned
    -0.06
    POSITIVE LOGITS
    转载èĩª
    0.07
    æľ´
    0.07
    Ä«b
    0.07
    以ä¸ĭåĨħ容
    0.07
    ske
    0.06
    æĥľ
    0.06
    èĭ±
    0.06
    KET
    0.06
    ATUS
    0.06
    (exports
    0.06
    Activations Density 0.553%

    No Known Activations