© 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. 27815
    Prev
    Next
    INDEX
    Explanations

    company or organization names

    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
    entifier
    -0.07
    Tiny
    -0.07
    IGH
    -0.07
    游åĪĥ
    -0.07
     pet
    -0.07
    oje
    -0.07
    CEED
    -0.07
    è¿ĻçĤ¹
    -0.07
    èĥ¯
    -0.07
    å®ł
    -0.07
    POSITIVE LOGITS
    æļ¨
    0.06
     consisting
    0.06
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    0.06
    å¾·éĺ³
    0.06
    idem
    0.06
    以任ä½ķ
    0.06
    ickets
    0.06
    dcc
    0.06
    marks
    0.06
    cape
    0.06
    Activations Density 0.246%

    No Known Activations