© 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. 25653
    Prev
    Next
    INDEX
    Explanations

    distance between items

    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
    _like
    -0.07
    andler
    -0.07
    íķĺ기를
    -0.07
    wäl
    -0.07
    Ãłn
    -0.07
    iore
    -0.07
    áĪį
    -0.07
    elius
    -0.07
    å½ĵçĿĢ
    -0.07
    forth
    -0.07
    POSITIVE LOGITS
    å¤ļè¿ľ
    0.07
    ä¸Ńå¿ĥçŃī
    0.07
    INESS
    0.07
     nearest
    0.06
     distance
    0.06
     any
    0.06
    ä¸Ńå¿ĥ
    0.06
     fixed
    0.06
    esch
    0.06
    ElementsBy
    0.06
    Activations Density 0.019%

    No Known Activations