© 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. 30826
    Prev
    Next
    INDEX
    Explanations

    Paul's trial

    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
    rette
    -0.08
    èģ
    -0.08
    OpenGL
    -0.08
    Thunk
    -0.08
    æĭŃ缮
    -0.08
    renc
    -0.07
    ress
    -0.07
    æĴ°æĸĩ
    -0.07
    çī¹å°Ķ
    -0.07
    ruck
    -0.07
    POSITIVE LOGITS
    redis
    0.07
    éķ¿æ²Ļ
    0.07
    hint
    0.07
    èĩªæĦĪ
    0.07
    stein
    0.06
    endra
    0.06
     prescribe
    0.06
    æĿ¡æĸĩ
    0.06
     Redis
    0.06
    agara
    0.06
    Activations Density 0.001%

    No Known Activations