© 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. 38539
    Prev
    Next
    INDEX
    Explanations

    cell or cells

    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
    egger
    -0.09
    est
    -0.09
    estig
    -0.08
    Ø©
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    yd
    -0.08
    htable
    -0.08
    oooooooo
    -0.08
    ìĦł
    -0.07
    onsin
    -0.07
    POSITIVE LOGITS
    ularity
    0.12
    ulaire
    0.10
    ular
    0.10
    ULAR
    0.10
    mates
    0.09
    liness
    0.09
    à¸Ľà¸£à¸°à¸ªà¸²à¸Ĺ
    0.08
    stial
    0.08
    wright
    0.08
    avanaugh
    0.08
    Activations Density 0.144%

    No Known Activations