© 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. 18767
    Prev
    Next
    INDEX
    Explanations

    blue colors

    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
    æķĻäºİ
    -0.09
    sa
    -0.08
    éĩij森
    -0.08
    ä¸ĩåįĥ
    -0.07
    çī©çļĦ
    -0.07
    stum
    -0.07
    si
    -0.07
    Åijl
    -0.07
    ãĥ£
    -0.07
    yled
    -0.07
    POSITIVE LOGITS
    berry
    0.13
    -grey
    0.11
    -green
    0.10
    berries
    0.10
    worthy
    0.10
    âtre
    0.09
    -headed
    0.09
    -eyed
    0.09
    -gray
    0.08
    headed
    0.08
    Activations Density 0.055%

    No Known Activations