© 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. 63259
    Prev
    Next
    INDEX
    Explanations

    ISP, aliments, stem, pension, saturation, hypnot, tab, MSC, Church, tip

    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
    htable
    -0.10
    entifier
    -0.09
    ificados
    -0.09
    chie
    -0.08
    ftime
    -0.08
    azier
    -0.08
    нд
    -0.08
    rolet
    -0.08
    ãĥĥãĤŃ
    -0.08
    anderia
    -0.08
    POSITIVE LOGITS
    /
    0.09
    èĴĤ
    0.07
     sav
    0.06
    -
    0.06
    sav
    0.06
    (
    0.06
    ow
    0.06
    ®
    0.06
    波波
    0.06
    ç°
    0.05
    Activations Density 1.431%

    No Known Activations