© 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. 11255
    Prev
    Next
    INDEX
    Explanations

    numbers and structures

    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
    สำà¸Ħัà¸įà¸Ĥà¸Ńà¸ĩ
    -0.07
    为åħ¬åı¸
    -0.07
    éĥ½ä¸º
    -0.07
    çī¹åħ¸
    -0.07
    ianos
    -0.07
    çŃĶæ¡Ī为
    -0.07
    shaw
    -0.07
    åħ¶ä¸º
    -0.07
    为åħ¶
    -0.06
    arella
    -0.06
    POSITIVE LOGITS
     sorts
    0.09
     interest
    0.09
     οÏĢοί
    0.09
    zelf
    0.08
    à¹Ģหลว
    0.08
    wegen
    0.08
     Interest
    0.08
    çİ¥
    0.08
    TEN
    0.08
    ufe
    0.08
    Activations Density 0.620%

    No Known Activations