© 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. 28503
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    leck
    -0.07
    ä½Ĩèĩ³å°ij
    -0.07
    akan
    -0.07
    PTY
    -0.07
    less
    -0.07
    èĩªå°Ĭå¿ĥ
    -0.07
    Times
    -0.07
    adam
    -0.06
    ograms
    -0.06
    imi
    -0.06
    POSITIVE LOGITS
    áŀľ
    0.08
    anford
    0.08
     (![
    0.08
    лле
    0.07
    ey
    0.07
    inach
    0.07
    çĬ¹
    0.07
    ç¼Ń
    0.07
    éįĭ
    0.07
    Dragging
    0.07
    Activations Density 0.000%

    No Known Activations