© 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. 18700
    Prev
    Next
    INDEX
    Explanations

    Modiano

    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
    ickl
    -0.06
    awl
    -0.06
    äºĨä¸ĭåİ»
    -0.06
    æĺ¯åIJ¦éľĢè¦ģ
    -0.06
    WB
    -0.06
    éĥ½æĺ¯æ¯Ķè¾ĥ
    -0.06
    éªĹ
    -0.06
    æĺ¯åIJ¦æĺ¯
    -0.06
     medi
    -0.06
     kie
    -0.06
    POSITIVE LOGITS
    .requireNonNull
    0.08
    .extract
    0.08
    hin
    0.07
    åĪĨæŀIJæ³ķ
    0.07
     Verst
    0.07
    rons
    0.07
    .scalar
    0.07
    ravo
    0.07
    eger
    0.07
     thankfully
    0.07
    Activations Density 0.002%

    No Known Activations