© 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. 31565
    Prev
    Next
    INDEX
    Explanations

    transitioning, initial state

    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
    ãģ«ãģĤãģŁ
    -0.07
    edException
    -0.06
    éģ¥è¿ľ
    -0.06
    代ãĤıãĤĬãģ«
    -0.06
    èĢħä¹Ł
    -0.06
    prices
    -0.06
    ä»·æł¼ä¹Ł
    -0.06
    umpang
    -0.06
    UEST
    -0.06
    зда
    -0.06
    POSITIVE LOGITS
    åĪĿå§ĭ
    0.14
    éĺ¶æ®µæĢ§
    0.13
     initial
    0.12
     transition
    0.12
    transition
    0.12
     transitioning
    0.11
     transitional
    0.11
    è¿ĩ渡
    0.11
     transitions
    0.11
     Initial
    0.11
    Activations Density 0.330%

    No Known Activations