© 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. 33548
    Prev
    Next
    INDEX
    Explanations

    Day News

    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
    оÑĩе
    -0.10
    &S
    -0.07
    &e
    -0.07
    &t
    -0.07
    æĦŁåĪ°äºĨ
    -0.07
    oces
    -0.07
     hinweg
    -0.06
    éĺĻ
    -0.06
    +c
    -0.06
    /io
    -0.06
    POSITIVE LOGITS
    Ả
    0.07
    æĥ³åĪ°è¿ĻéĩĮ
    0.07
    åı£æ°Ķ
    0.07
    enes
    0.07
    ëĤ©
    0.07
    _props
    0.06
     startPosition
    0.06
    æ¬ł
    0.06
    omÄĽ
    0.06
    å²Ĥ
    0.06
    Activations Density 0.004%

    No Known Activations