© 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. 3370
    Prev
    Next
    INDEX
    Explanations

    who followed by a verb

    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
    ments
    -0.08
    ÏĨÏħ
    -0.08
    деÑı
    -0.08
    reicher
    -0.07
    spent
    -0.07
    à¸ģารà¸ĵà¹Į
    -0.07
    اتÙĩÙħ
    -0.07
    urator
    -0.07
    uned
    -0.07
    гÑĸ
    -0.07
    POSITIVE LOGITS
    soever
    0.14
     else
    0.12
    _else
    0.10
    else
    0.09
    /how
    0.09
    oping
    0.09
    	else
    0.09
    θεν
    0.08
    ذا
    0.08
    quam
    0.08
    Activations Density 0.115%

    No Known Activations