© 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. 64656
    Prev
    Next
    INDEX
    Explanations

    FOR A PARTICULAR PURPOSE

    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
    _REASON
    -0.07
    ois
    -0.07
     rad
    -0.07
    udit
    -0.06
    éĢļ
    -0.06
    诱
    -0.06
    emi
    -0.06
    enton
    -0.06
    lsen
    -0.06
    åı°
    -0.06
    POSITIVE LOGITS
    amai
    0.09
    Ø·Ùģ
    0.08
     Äijâu
    0.08
    aldi
    0.08
    ivar
    0.07
    _arguments
    0.07
    igham
    0.07
    çļĦäºĭæĥħäºĨ
    0.07
    å¦Ĥæľīä¾µæĿĥ
    0.07
    apphire
    0.07
    Activations Density 0.002%

    No Known Activations