© 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. 63304
    Prev
    Next
    INDEX
    Explanations

    code syntax and parameters

    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
    θÏį
    -0.08
     undes
    -0.08
    ntl
    -0.08
    YRO
    -0.08
    abis
    -0.08
    λλη
    -0.07
    ortun
    -0.07
    æŃ»äºº
    -0.07
    -meta
    -0.07
    /meta
    -0.07
    POSITIVE LOGITS
    èĻ½çĦ¶æĺ¯
    0.07
     Nich
    0.07
    å¯Ĩ
    0.07
    efeld
    0.06
    åIJ«æľīçļĦ
    0.06
    iget
    0.06
    å¼ķ导
    0.06
    ows
    0.06
    èĻ½çĦ¶æ²¡æľī
    0.06
    æ·ĺ
    0.06
    Activations Density 0.003%

    No Known Activations