© 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. 46222
    Prev
    Next
    INDEX
    Explanations

    per capita or per pupil

    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
    sstr
    -0.08
    æĽľ
    -0.08
    eszt
    -0.08
    ½
    -0.07
    erot
    -0.07
    ä¸ĭä¸Ģ级
    -0.07
    åī²å¼ķ
    -0.07
    åķ¸
    -0.07
    gens
    -0.07
     Soares
    -0.07
    POSITIVE LOGITS
    人åĿĩ
    0.08
    çļĦå¹³åĿĩ
    0.08
    /share
    0.08
     capita
    0.07
     average
    0.07
    å½ĵãģŁãĤĬ
    0.07
    -vars
    0.07
    åħįåĨł
    0.07
    isNew
    0.07
    æ¯Ķä¸Ĭå¹´
    0.07
    Activations Density 0.027%

    No Known Activations