© 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. 43802
    Prev
    Next
    INDEX
    Explanations

    latest news

    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
    aison
    -0.10
    Ñģев
    -0.09
    꽤
    -0.09
    instanc
    -0.09
    izio
    -0.09
    itto
    -0.09
    vette
    -0.09
    uez
    -0.09
    ystone
    -0.09
    brero
    -0.09
    POSITIVE LOGITS
    ened
    0.08
    ç¨ĭ度ä¸Ĭ
    0.08
    åĽŀäºĭ
    0.07
    ening
    0.07
    ãĤĤãģ®ãģ§
    0.07
    c
    0.06
     regard
    0.06
     halnya
    0.06
    çĦ¶æĺ¯
    0.06
    ose
    0.06
    Activations Density 0.001%

    No Known Activations