© 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. 17903
    Prev
    Next
    INDEX
    Explanations

    sides, duo, ventures, recorded, peace, together, doubles

    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
    èĢĺ
    -0.07
    ott
    -0.06
    cae
    -0.06
    ilas
    -0.06
    åıĬåIJĦ
    -0.06
    ambi
    -0.06
    uia
    -0.06
    ennem
    -0.06
    illi
    -0.06
    ä½ij
    -0.06
    POSITIVE LOGITS
    åħ¶ä¸İ
    0.20
    åı¯ä¸İ
    0.19
    å®ĥä¸İ
    0.18
    รà¹Īวมà¸ģัà¸ļ
    0.18
    å·²ä¸İ
    0.18
    ä¸İåħ¶ä»ĸ
    0.18
    åı¯ä»¥ä¸İ
    0.17
    åĪĨåĪ«ä¸İ
    0.17
    ä»ĸä¸İ
    0.17
    ìĻĢìĿĺ
    0.17
    Activations Density 0.492%

    No Known Activations