© 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. 18247
    Prev
    Next
    INDEX
    Explanations

    California, class II, week

    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
    inger
    -0.07
    çĨł
    -0.07
    mun
    -0.07
    arjo
    -0.07
    ãĥĬãĥ¼
    -0.06
    æijĩ
    -0.06
    èĬ±åĦ¿
    -0.06
    -counter
    -0.06
    çĥ¬
    -0.06
    ilt
    -0.06
    POSITIVE LOGITS
    第ä¸Ģç§į
    0.08
    vers
    0.08
    elson
    0.07
    akah
    0.07
    以å¾ħ
    0.07
    à¹īà¸Ńมูล
    0.07
    над
    0.07
    verso
    0.07
    зд
    0.07
    ÙĪاد
    0.07
    Activations Density 0.184%

    No Known Activations