© 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. 39138
    Prev
    Next
    INDEX
    Explanations

    bb followed by R, C, or Z

    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
    åĦ¿çļĦ
    -0.09
    -ever
    -0.09
    åĦ¿
    -0.08
    ¯
    -0.08
    åħĴ
    -0.08
    à»Ī
    -0.08
    yle
    -0.07
    usza
    -0.07
    ¬
    -0.07
    essen
    -0.07
    POSITIVE LOGITS
    ness
    0.10
    ÑģÑı
    0.10
    çĦ¶
    0.08
    ful
    0.08
    ÙħاÙĨ
    0.07
    Ùħ
    0.07
    ron
    0.07
    ল
    0.07
    azzo
    0.07
    ÛĮ
    0.07
    Activations Density 0.011%

    No Known Activations