© 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. 9377
    Prev
    Next
    INDEX
    Explanations

    polynomials in k[x,y]

    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
    ä¸įåľ¨
    -0.07
    oose
    -0.07
     Ñģквоз
    -0.06
    rika
    -0.06
    触åĬ¨
    -0.06
    åħīæĺİ
    -0.06
    man
    -0.06
    mium
    -0.06
    触
    -0.06
    stück
    -0.06
    POSITIVE LOGITS
    å°ijåħĪéĺŁåijĺ
    0.08
    viz
    0.08
    ingham
    0.08
    ##_
    0.07
    ercul
    0.07
    ezo
    0.07
    齡
    0.07
    arias
    0.07
    qed
    0.07
    é¾Ħ
    0.07
    Activations Density 0.006%

    No Known Activations