© 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. 55605
    Prev
    Next
    INDEX
    Explanations

    from std to or from a

    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
    ossi
    -0.07
    prib
    -0.07
    _snd
    -0.07
    EGA
    -0.07
    rani
    -0.07
    spre
    -0.07
    inei
    -0.07
    亲身ä½ĵ
    -0.06
    apis
    -0.06
    ×Ļר×ķ
    -0.06
    POSITIVE LOGITS
    worth
    0.08
     given
    0.08
    ноп
    0.08
    åĢ¼å¾Ĺ
    0.08
    cratch
    0.07
     verilen
    0.07
    given
    0.07
    iven
    0.07
     worth
    0.07
    paramref
    0.07
    Activations Density 0.215%

    No Known Activations