© 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. 18304
    Prev
    Next
    INDEX
    Explanations

    `long` parameter for routes/directions

    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
    éĩijåĪ¸
    -0.08
    åĬłåħ³æ³¨
    -0.08
    é£İèµ·
    -0.08
    æīĢåѦçļĦ
    -0.08
    å®ļäºİ
    -0.08
    oding
    -0.07
    sic
    -0.07
    æľĢåħĪè¿ĽçļĦ
    -0.07
    urso
    -0.07
     tearDown
    -0.07
    POSITIVE LOGITS
    åĮ¹
    0.07
    .codec
    0.07
    avage
    0.07
    ç¿»
    0.07
    å¿ł
    0.06
    æĭīå¾·
    0.06
    hyd
    0.06
    çŁ
    0.06
    å¿łè¯ļ
    0.06
    é£ĺ
    0.06
    Activations Density 0.004%

    No Known Activations