© 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. 12030
    Prev
    Next
    INDEX
    Explanations

    combined or both

    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
    ×ķ×ĸ
    -0.07
     Contrast
    -0.07
    æŬ
    -0.06
    CLS
    -0.06
     drastically
    -0.06
     contrast
    -0.06
    åīĬ
    -0.06
    rocÅĤaw
    -0.06
    éĿ¢å±Ĥ
    -0.06
    è¦ģèµ°
    -0.06
    POSITIVE LOGITS
    combined
    0.13
     combined
    0.13
    ä¸Ģ并
    0.13
    Combined
    0.12
     jointly
    0.11
     combines
    0.11
     BOTH
    0.11
     kombini
    0.11
     gabungan
    0.11
    åħ¼åħ·
    0.11
    Activations Density 0.257%

    No Known Activations