© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30234
    Prev
    Next
    INDEX
    Explanations

    references, composition, coordinates, comparison

    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
    лан
    -0.07
    ÑĬв
    -0.07
    åİŁä»¶åıĬå¤įåį°ä»¶
    -0.07
    indy
    -0.06
    .VERSION
    -0.06
     dÃłn
    -0.06
    åİĮåĢ¦
    -0.06
     vlast
    -0.06
     ì²ĺ
    -0.06
    ammo
    -0.06
    POSITIVE LOGITS
    —which
    0.09
    èĸ°
    0.09
    ä¼Ĺ
    0.07
    åĮ®
    0.07
     Indah
    0.07
    åįļæĸĩ
    0.06
     lequel
    0.06
    iana
    0.06
    which
    0.06
    quiv
    0.06
    Activations Density 0.007%

    No Known Activations