© 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. 43143
    Prev
    Next
    INDEX
    Explanations

    ratio / probability / frequency

    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
    avig
    -0.08
    wright
    -0.07
    çħ§çĿĢ
    -0.07
    rza
    -0.07
    >p
    -0.07
    åħ¬æ¬¾
    -0.07
    [++
    -0.06
    brero
    -0.06
    >+
    -0.06
    ä¸Ģ鸣
    -0.06
    POSITIVE LOGITS
    ếm
    0.08
    åįłæ¯Ķ
    0.08
    tracer
    0.07
     доле
    0.07
    åįł
    0.07
    _relative
    0.07
    åįłæĢ»
    0.07
    ollar
    0.07
    黯çĦ¶
    0.07
    anny
    0.07
    Activations Density 0.019%

    No Known Activations