© 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. 16722
    Prev
    Next
    INDEX
    Explanations

    slopes

    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
    ê½ĥ
    -0.08
    ness
    -0.08
    bies
    -0.08
    ignment
    -0.07
    lia
    -0.07
     Eppure
    -0.07
    scoped
    -0.07
    å·¥ä¸ļåįıä¼ļ
    -0.07
    onos
    -0.07
    æīĢåij¨
    -0.06
    POSITIVE LOGITS
    less
    0.13
    etting
    0.09
    lessness
    0.09
    -less
    0.09
    Ö¼
    0.08
    LESS
    0.08
    arity
    0.08
    licate
    0.08
    koch
    0.08
    inheit
    0.08
    Activations Density 0.005%

    No Known Activations