© 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. 42314
    Prev
    Next
    INDEX
    Explanations

    special characters or encoding issues

    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
    en
    -0.10
    ed
    -0.10
    ation
    -0.09
    ic
    -0.09
    ing
    -0.08
    an
    -0.08
    ÙĬØ©
    -0.08
    al
    -0.07
    a
    -0.07
    ãĥ³
    -0.07
    POSITIVE LOGITS
    ¦
    0.12
    ————————————————
    0.11
    Ī
    0.11
    ¤
    0.10
    ï¸İ
    0.10
    presso
    0.10
    ª
    0.09
    ¥
    0.09
    ħ
    0.09
    Ħ
    0.09
    Activations Density 0.011%

    No Known Activations