© 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. 33947
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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
    chaft
    -0.08
    sville
    -0.08
    æĪĸåĽł
    -0.08
    eggi
    -0.08
    ÃŃmp
    -0.08
    heets
    -0.08
    spath
    -0.08
    leter
    -0.08
    æłĸ
    -0.08
    tere
    -0.08
    POSITIVE LOGITS
     involving
    0.09
     involved
    0.08
    q
    0.07
    an
    0.07
    æ¶īåıĬåĪ°
    0.07
    æ³ķåĻ¨
    0.06
    yd
    0.06
     envolvendo
    0.06
     scalar
    0.06
    un
    0.06
    Activations Density 0.010%

    No Known Activations