© 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. 19820
    Prev
    Next
    INDEX
    Explanations

    number of other things

    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
    inters
    -0.09
    åĩ«
    -0.08
    atham
    -0.08
     Ving
    -0.08
    elok
    -0.08
    веÑĢи
    -0.08
    äsche
    -0.08
    ummies
    -0.07
    ftime
    -0.07
    ãģªãģĦãģ¨
    -0.07
    POSITIVE LOGITS
    åħ¶ä»ĸ
    0.10
     other
    0.10
    other
    0.09
     factors
    0.08
    åħ¶å®ĥ
    0.08
     Other
    0.08
     reasons
    0.08
    _other
    0.08
    æī©å±ķèµĦæĸĻ
    0.07
     aspects
    0.07
    Activations Density 1.095%

    No Known Activations