© 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. 55850
    Prev
    Next
    INDEX
    Explanations

    mathematician, biologist, organist, ophthalmologist, scholar

    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
    _COMPAT
    -0.08
    itled
    -0.08
    ±
    -0.08
    å¹²ç²ī
    -0.07
    éªĮèµĦ
    -0.07
    ign
    -0.07
    kirchen
    -0.07
    åľ¨çº¿çķĻè¨Ģ
    -0.07
    ikian
    -0.07
    ervlet
    -0.07
    POSITIVE LOGITS
    sh
    0.07
    è©«
    0.06
    sert
    0.06
    ssa
    0.06
     prevision
    0.06
    หย
    0.06
    isant
    0.06
    imon
    0.06
    late
    0.06
    lef
    0.06
    Activations Density 0.001%

    No Known Activations