© 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. 50471
    Prev
    Next
    INDEX
    Explanations

    copyright `)`

    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
     Hal
    -0.08
    寡
    -0.07
    ế
    -0.07
    INU
    -0.07
    jab
    -0.07
     hal
    -0.07
    :Event
    -0.06
    æģ¯
    -0.06
    &e
    -0.06
    :///
    -0.06
    POSITIVE LOGITS
    esson
    0.07
    ronic
    0.07
     Flip
    0.07
    /ref
    0.07
    icates
    0.07
    该楼å±Ĥ
    0.07
     psychic
    0.06
    erder
    0.06
    Flip
    0.06
    preferred
    0.06
    Activations Density 0.004%

    No Known Activations