© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26766
    Prev
    Next
    INDEX
    Explanations

    provided 'as-is' or under license

    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
    erÃŃa
    -0.12
    er
    -0.12
    azón
    -0.09
    shots
    -0.09
    roads
    -0.09
    ostr
    -0.09
    stens
    -0.09
    ically
    -0.09
    itude
    -0.09
    pected
    -0.08
    POSITIVE LOGITS
    ت
    0.10
    м
    0.09
    zelfde
    0.09
    elor
    0.08
    ়
    0.08
    ķ
    0.08
    sver
    0.07
    erness
    0.07
    e
    0.07
    ãģĺãĤģãģ¦
    0.07
    Activations Density 0.067%

    No Known Activations