© 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. 21202
    Prev
    Next
    INDEX
    Explanations

    addressing you

    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
    amente
    -0.08
    Ø´
    -0.08
    oczy
    -0.08
    åľ¨èº«è¾¹
    -0.08
    Ø´ÙĪ
    -0.07
    ste
    -0.07
    åĮ»çĶŁè¯´
    -0.07
    ric
    -0.07
    maÃŁen
    -0.07
    γά
    -0.07
    POSITIVE LOGITS
    'll
    0.12
    're
    0.11
     stessi
    0.10
    sse
    0.10
    ’ll
    0.09
    ’re
    0.09
    've
    0.09
    er
    0.09
    -même
    0.09
    self
    0.09
    Activations Density 0.335%

    No Known Activations