© 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. 58061
    Prev
    Next
    INDEX
    Explanations

    flow or transfer

    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
    eno
    -0.08
    sud
    -0.07
    åĨħå¤ĸ
    -0.07
    ẻ
    -0.07
    åıĬå®īåħ¨
    -0.06
    jie
    -0.06
     clientele
    -0.06
    &#
    -0.06
    à¦Ń
    -0.06
    shell
    -0.06
    POSITIVE LOGITS
    rase
    0.08
    zers
    0.08
    rasil
    0.08
    ovel
    0.07
     sekaligus
    0.07
    rys
    0.07
    ultas
    0.06
    ride
    0.06
    æľĢåIJİè¿ĺæĺ¯
    0.06
    ÑĢиÑģÑĤ
    0.06
    Activations Density 0.032%

    No Known Activations