© 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. 4380
    Prev
    Next
    INDEX
    Explanations

    work or working

    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
    enny
    -0.08
    æīĩ
    -0.08
    anol
    -0.08
    æľ¬æĢ§
    -0.07
    éŁ¿
    -0.07
    oton
    -0.07
    ç½·
    -0.07
    rael
    -0.07
    rstrip
    -0.07
    zar
    -0.07
    POSITIVE LOGITS
     backwards
    0.08
     teb
    0.08
    INK
    0.07
    INCI
    0.07
    çĥ¨
    0.06
    omes
    0.06
     hal
    0.06
    è©°
    0.06
    oga
    0.06
    æı£
    0.06
    Activations Density 0.001%

    No Known Activations