© 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. 3519
    Prev
    Next
    INDEX
    Explanations

    ach or BCML

    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
    igh
    -0.08
    ÚĨار
    -0.07
    atic
    -0.07
     CircularProgress
    -0.07
    åħ¶äºĭ
    -0.07
    gable
    -0.07
    κÏģα
    -0.07
    embl
    -0.07
    пÑĬл
    -0.07
    lessly
    -0.07
    POSITIVE LOGITS
    ademia
    0.12
    nowled
    0.09
    ories
    0.09
    opyright
    0.09
    arya
    0.09
    ãĤĪãģĨãģª
    0.09
    rist
    0.08
    stum
    0.08
    ymar
    0.08
    allenge
    0.08
    Activations Density 0.943%

    No Known Activations