© 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. 51458
    Prev
    Next
    INDEX
    Explanations

    specific searching or filtering

    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
     Manh
    -0.08
    vez
    -0.07
    öp
    -0.07
     appropriate
    -0.07
     complementary
    -0.06
    APH
    -0.06
    rors
    -0.06
    涨äºĨ
    -0.06
    å®ī妮
    -0.06
    éĢłè¡Ģ
    -0.06
    POSITIVE LOGITS
    çī¹å®ļ
    0.15
    æĮĩå®ļ
    0.14
    çī¹å®ļçļĦ
    0.14
    æĮĩå®ļçļĦ
    0.13
     specified
    0.13
    çī¹å®ļãģ®
    0.13
     íĬ¹ìłķ
    0.13
     tertentu
    0.12
    specified
    0.11
     especÃŃfica
    0.11
    Activations Density 0.338%

    No Known Activations