© 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. 29622
    Prev
    Next
    INDEX
    Explanations

    absolutely nothing

    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
    COPY
    -0.07
    ioned
    -0.07
    erias
    -0.07
    å¯
    -0.07
    krit
    -0.07
    ancis
    -0.07
    å½Ĵå±ŀäºİä¸Ĭå¸Ĥåħ¬åı¸èĤ¡ä¸ľçļĦ
    -0.07
    ĵĺ
    -0.07
    _inline
    -0.07
    #
    -0.07
    POSITIVE LOGITS
    ambre
    0.07
    IPC
    0.07
    Interop
    0.07
    odus
    0.06
    è¿IJçŃ¹
    0.06
    èķ
    0.06
    agenda
    0.06
     anecd
    0.06
     multiply
    0.06
    çĭĻ
    0.06
    Activations Density 0.001%

    No Known Activations