© 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. 47117
    Prev
    Next
    INDEX
    Explanations

    st followed by code/symbols

    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
    ãĥ³ãĥī
    -0.07
    çīĪæĿĥéĹ®é¢ĺ
    -0.07
    iare
    -0.07
    æµ®çĶŁ
    -0.07
    neau
    -0.07
    à°¸à±ģ
    -0.06
     rẽ
    -0.06
    urale
    -0.06
    ::_
    -0.06
    ìĭľëĭ¤
    -0.06
    POSITIVE LOGITS
    gebracht
    0.07
    illot
    0.07
    olling
    0.07
    cript
    0.06
    ·¸
    0.06
    èĥ½åĬĽåıĬ
    0.06
    rina
    0.06
    vided
    0.06
    æĮ
    0.06
    éĴ³
    0.06
    Activations Density 0.003%

    No Known Activations