© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61853
    Prev
    Next
    INDEX
    Explanations

    reporting abuse or violations

    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
    xffffffff
    -0.08
    ggio
    -0.08
    .asc
    -0.07
    gli
    -0.07
    IZAR
    -0.07
    adro
    -0.07
    elmet
    -0.07
    é¡·
    -0.07
    igne
    -0.07
    (TRUE
    -0.07
    POSITIVE LOGITS
    holt
    0.07
    ç¿»äºĨ
    0.07
    astian
    0.07
    oleon
    0.06
    ton
    0.06
    áºŃy
    0.06
    åī¯ç»Ħéķ¿
    0.06
    çĨĦ
    0.06
    _delegate
    0.06
    å°±è¿Ļæł·
    0.06
    Activations Density 0.002%

    No Known Activations