© 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. 16669
    Prev
    Next
    INDEX
    Explanations

    right or left

    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
    éĶ¦æ¶Ľ
    -0.08
    ä¸ī两
    -0.08
    enario
    -0.08
    uston
    -0.08
    éĢ£ä¼ij
    -0.08
    ozo
    -0.08
     Civile
    -0.08
    lon
    -0.08
    ervised
    -0.08
    äºĨä¸ĢæŃ¥
    -0.08
    POSITIVE LOGITS
    ness
    0.10
    maz
    0.07
    ä»İæĹł
    0.07
    оÑģÑĮ
    0.07
    iness
    0.07
    mun
    0.06
    set
    0.06
    äl
    0.06
    ods
    0.06
    nya
    0.06
    Activations Density 0.007%

    No Known Activations