© 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. 58009
    Prev
    Next
    INDEX
    Explanations

    month and year

    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
    imd
    -0.07
    iola
    -0.07
    ething
    -0.07
    ilah
    -0.07
    encia
    -0.06
    Aura
    -0.06
    ä¸Ģæĭį
    -0.06
    -render
    -0.06
    IMIT
    -0.06
    odesk
    -0.06
    POSITIVE LOGITS
    Âł
    0.09
     Âł
    0.08
    èĩªè¨Ģ
    0.07
    éŁ³
    0.07
    assistant
    0.07
     Âł Âł
    0.07
    ³³
    0.07
    abt
    0.07
    ³³³³³³³
    0.06
    tait
    0.06
    Activations Density 0.062%

    No Known Activations