© 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. 32707
    Prev
    Next
    INDEX
    Explanations

    sorting and data structures

    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
    оÑħ
    -0.06
     childs
    -0.06
    att
    -0.06
    楷
    -0.06
    à¯įவ
    -0.06
    祺
    -0.06
    大çIJĨ
    -0.06
    驹
    -0.06
    wg
    -0.05
    åĩŃ
    -0.05
    POSITIVE LOGITS
    éĩijå®Ŀ
    0.10
     TestBed
    0.08
    YPES
    0.08
    .gnu
    0.08
    LOTS
    0.08
    icale
    0.08
    ungsweise
    0.08
    æĽ´æĸ°æĹ¥æľŁ
    0.08
    egos
    0.08
    CharArray
    0.07
    Activations Density 0.001%

    No Known Activations