© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42193
    Prev
    Next
    INDEX
    Explanations

    individual components

    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
    atia
    -0.06
    exus
    -0.06
    _INLINE
    -0.06
    æ§
    -0.06
    ستÙĩ
    -0.06
    idad
    -0.06
    adrat
    -0.06
    igel
    -0.06
    -gnu
    -0.06
    两类
    -0.06
    POSITIVE LOGITS
     individually
    0.15
    åIJĦèĩª
    0.13
    åIJĦèĩªçļĦ
    0.13
     individual
    0.12
    individ
    0.12
     individuais
    0.12
    åIJĦåħ·
    0.11
     Individual
    0.11
    çĭ¬ç«ĭ
    0.11
    åIJĦæľīåIJĦ
    0.10
    Activations Density 0.072%

    No Known Activations