© 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. 12520
    Prev
    Next
    INDEX
    Explanations

    <code>pm</code>

    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
    ä»Ģä¹Īæł·
    -0.08
    .mk
    -0.07
    ibold
    -0.07
    lish
    -0.07
    管çIJĨå¤Ħ
    -0.07
    indust
    -0.07
    adier
    -0.07
    ORY
    -0.07
    Slides
    -0.07
    esk
    -0.07
    POSITIVE LOGITS
     dime
    0.07
    zor
    0.07
    ÑģаÑĢ
    0.06
    karya
    0.06
    ILD
    0.06
    åįķ项
    0.06
     Phillips
    0.06
    ãģĭãģij
    0.06
    Ñīи
    0.06
     eventType
    0.06
    Activations Density 0.002%

    No Known Activations