© 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. 61579
    Prev
    Next
    INDEX
    Explanations

    parent, representative, element, class, diagram

    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
    shot
    -0.08
    纨
    -0.07
    uncate
    -0.07
    æĸĽ
    -0.07
    éªĭ
    -0.07
     bree
    -0.07
    -fit
    -0.07
    æ¯Ļ
    -0.07
    schuss
    -0.07
     fit
    -0.07
    POSITIVE LOGITS
    çĪ¬åĪ°
    0.08
     ig
    0.07
    allocator
    0.07
     bitmask
    0.07
     heg
    0.07
    é¢Ĩåħ»
    0.07
    é¢Ĩåľ°
    0.07
    owns
    0.07
     pointer
    0.07
    èĩªæ²»
    0.06
    Activations Density 0.002%

    No Known Activations