© 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. 61240
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    quee
    -0.07
    å¤§ä½ľ
    -0.07
    rzy
    -0.07
     sever
    -0.07
    erer
    -0.07
    Arm
    -0.07
    ryw
    -0.07
    大礼
    -0.07
    裾
    -0.07
    ROID
    -0.06
    POSITIVE LOGITS
    htë
    0.07
    ñas
    0.07
    aga
    0.07
     sku
    0.07
    Scrollbar
    0.07
    ÅĽc
    0.06
    scroll
    0.06
    afen
    0.06
    éĹ
    0.06
    ä¸ĵäººè´Łè´£
    0.06
    Activations Density 0.191%

    No Known Activations