© 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. 21280
    Prev
    Next
    INDEX
    Explanations

    executable schemas or code base

    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
    åįłæĢ»
    -0.07
    lea
    -0.07
     dem
    -0.07
    åįłçĶ¨
    -0.07
    -dem
    -0.07
    xFFFFFF
    -0.07
    è¡Ģ管çĺ¤
    -0.07
    åįĬéĢĶ
    -0.07
    åįł
    -0.07
    -density
    -0.07
    POSITIVE LOGITS
     assembled
    0.09
    asher
    0.08
     resultant
    0.08
     spont
    0.08
    .comp
    0.08
     composite
    0.08
    robat
    0.07
     Harness
    0.07
    éªĮ
    0.07
    æŃ£åĢ¼
    0.07
    Activations Density 0.001%

    No Known Activations