© 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. 63230
    Prev
    Next
    INDEX
    Explanations

    at any time

    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
    owa
    -0.07
    paring
    -0.07
    еÑĤи
    -0.07
    اخ
    -0.07
    -Type
    -0.07
    Ùħج
    -0.07
    ä¸īå¹´æĿ¥
    -0.06
    æĪªæŃ¢çĽ®åīį
    -0.06
    åħŃåIJĪ
    -0.06
    äºĶèī²
    -0.06
    POSITIVE LOGITS
    ä»Ģä¹Īåľ°æĸ¹
    0.10
     anywhere
    0.08
    anner
    0.08
    tempts
    0.08
    cala
    0.08
    orney
    0.08
     jun
    0.08
    ä½ķå¤Ħ
    0.08
    ä»»ä½ķæŶåĢĻ
    0.07
     times
    0.07
    Activations Density 0.075%

    No Known Activations