© 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. 57422
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ãng
    -0.10
    å·¡è§Ĩåijĺ
    -0.09
    enho
    -0.09
    à®±à¯įப
    -0.09
    è¶Ĭèµ°
    -0.08
    angu
    -0.08
    åİĭå²ģ
    -0.08
    isas
    -0.08
    çĤºä½ķ
    -0.08
    anford
    -0.08
    POSITIVE LOGITS
    (
    0.08
    Âł
    0.07
    /
    0.07
    ä¸įåĴĮ
    0.07
    延
    0.07
    -
    0.07
    ↵
    0.07
    à¹Īà¸Ńà¸Ļ
    0.07
    为æķ°
    0.06
    "
    0.06
    Activations Density 0.553%

    No Known Activations

    This feature has no known activations.