© 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. 21110
    Prev
    Next
    INDEX
    Explanations

    acoustic phenomena and applications

    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
     volna
    -0.07
    ogue
    -0.07
    alism
    -0.07
    atism
    -0.06
    itorial
    -0.06
    czyn
    -0.06
    asmine
    -0.06
     Ñģобой
    -0.06
    zin
    -0.06
    anging
    -0.06
    POSITIVE LOGITS
    åĽĽæº¢
    0.08
    olean
    0.08
    zept
    0.08
    -opt
    0.08
    dessen
    0.08
    icch
    0.08
    uard
    0.08
    bite
    0.08
    俳
    0.08
    onical
    0.08
    Activations Density 0.018%

    No Known Activations