© 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. 10307
    Prev
    Next
    INDEX
    Explanations

    National park, taxes, prints

    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
    ä»ķ
    -0.07
    иж
    -0.06
    trol
    -0.06
    éĥģ
    -0.06
    空ä¸Ń
    -0.06
    estik
    -0.06
    lian
    -0.06
    MP
    -0.06
    èĶ
    -0.06
    çľĭ好
    -0.06
    POSITIVE LOGITS
    oga
    0.08
    åĸľæĢĴ
    0.07
    utherland
    0.07
    ore
    0.07
    odzi
    0.07
    è¡Įä¹ĭ
    0.07
    åĪĺ家
    0.07
    plin
    0.07
    两çĶ¨
    0.07
    zik
    0.07
    Activations Density 0.262%

    No Known Activations