© 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. 58134
    Prev
    Next
    INDEX
    Explanations

    symbols, numbers, and website references

    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
    attles
    -0.07
    clar
    -0.07
    æ²īéĩį
    -0.07
    å¨Ĩ
    -0.07
    æĿŁ
    -0.07
    å¿ĥçĥ¦
    -0.07
    åIJĵ
    -0.07
    alte
    -0.07
    ugg
    -0.07
    rief
    -0.06
    POSITIVE LOGITS
    å¼±èĢħ
    0.07
     adept
    0.07
    StateMachine
    0.07
    å¿ħçĦ¶æĺ¯
    0.07
    ince
    0.07
    agaan
    0.07
     lưỡng
    0.07
    çļĦ两个
    0.07
     Bris
    0.07
    çĬ¶åħĥ
    0.06
    Activations Density 0.004%

    No Known Activations