© 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. 32550
    Prev
    Next
    INDEX
    Explanations

    estrogen, beta, AT&T

    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
    pv
    -0.08
    p
    -0.07
    cion
    -0.06
    ãĤĮ
    -0.06
    pip
    -0.06
    ll
    -0.06
     fid
    -0.06
    èĢĮéĢĻ
    -0.06
    ff
    -0.06
    li
    -0.06
    POSITIVE LOGITS
    erstra
    0.09
    anyol
    0.09
    ä»»ä½ķåħ¶ä»ĸ
    0.08
     Grosso
    0.08
    acce
    0.08
    icap
    0.08
     diagnosti
    0.08
    verkehr
    0.07
    atron
    0.07
    (er
    0.07
    Activations Density 0.227%

    No Known Activations