© 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. 57769
    Prev
    Next
    INDEX
    Explanations

    version numbers and dates

    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
    _EVAL
    -0.07
    å®ĥåħ·æľī
    -0.07
    gam
    -0.07
    ron
    -0.07
    ivu
    -0.06
    åIJ¸æĶ¶
    -0.06
    èĤ¡
    -0.06
    plant
    -0.06
    æ¡¥éķĩ
    -0.06
     Spl
    -0.06
    POSITIVE LOGITS
    ensial
    0.08
    resses
    0.08
     Initialized
    0.08
    atoes
    0.08
    arks
    0.07
    çĴĭ
    0.07
    amakan
    0.07
    urre
    0.07
    è®¤çľŁç»Ħç»ĩ
    0.07
    adders
    0.07
    Activations Density 0.047%

    No Known Activations