© 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. 48169
    Prev
    Next
    INDEX
    Explanations

    per unit of measure

    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
    zilla
    -0.08
    terer
    -0.07
    å·¥ä½ľä½ľé£İ
    -0.07
    å·¥ä½ľå¹´éĻIJ
    -0.07
     Thao
    -0.07
    à¹ģà¸ģà¹Ī
    -0.06
     Kalimantan
    -0.06
    ysin
    -0.06
    en
    -0.06
    ä¿Ń
    -0.06
    POSITIVE LOGITS
    /of
    0.07
     οÏĢοίο
    0.07
    weisen
    0.07
     quals
    0.07
     annum
    0.07
    kada
    0.07
    onnées
    0.07
    mdb
    0.07
    /about
    0.07
    å®ģæµ·
    0.07
    Activations Density 0.032%

    No Known Activations