© 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. 46145
    Prev
    Next
    INDEX
    Explanations

    review, benchmark, migration, log, configure, analysis, departments, compare, report

    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
    venta
    -0.08
     Went
    -0.08
    ombre
    -0.08
     Liber
    -0.07
    ,map
    -0.07
    ãĥĭãĤ¢
    -0.07
    éĢŀ
    -0.07
    quine
    -0.07
    agina
    -0.07
    Stride
    -0.07
    POSITIVE LOGITS
    æĢ¥éľĢ
    0.07
     keyed
    0.06
     radi
    0.06
    对è¿Ļ
    0.06
    注
    0.06
    æī©å¤§
    0.06
    è¿Ļæī¹
    0.06
    KW
    0.06
    èį¼
    0.06
    äºĨä¸Ģæī¹
    0.06
    Activations Density 0.241%

    No Known Activations