© 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. 50232
    Prev
    Next
    INDEX
    Explanations

    concepts and states

    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
    åIJĦèĩªçļĦ
    -0.09
    leurs
    -0.09
    åIJĦèĩª
    -0.08
    leur
    -0.08
     whose
    -0.07
    约èĢĮåIJĮ
    -0.07
    å²ij
    -0.07
    æ±Ĥæĺ¯
    -0.07
    龸
    -0.06
    MED
    -0.06
    POSITIVE LOGITS
    æĽĻ
    0.08
     aspects
    0.07
     practices
    0.07
    avings
    0.07
    notations
    0.07
     elsewhere
    0.07
    ä¸įè°Ī
    0.07
     rig
    0.07
    defaults
    0.07
     cuckold
    0.07
    Activations Density 0.523%

    No Known Activations