© 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. 38121
    Prev
    Next
    INDEX
    Explanations

    junction obstruction

    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
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    -0.07
     efforts
    -0.07
    aims
    -0.07
    zam
    -0.07
    fully
    -0.06
    ä¹ĭåĪĹ
    -0.06
    elos
    -0.06
    ISTR
    -0.06
    _EXTENSIONS
    -0.06
    ayaan
    -0.06
    POSITIVE LOGITS
    å¤ĦçļĦ
    0.14
    å¤Ħ
    0.13
    èĻķçļĦ
    0.11
    éĻĦè¿ijçļĦ
    0.11
    /interface
    0.10
    éĻĦè¿ij
    0.10
    between
    0.10
    çŃīå¤Ħ
    0.09
    èĻķ
    0.09
    å¤Ħéķ¿
    0.09
    Activations Density 0.107%

    No Known Activations