© 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. 55401
    Prev
    Next
    INDEX
    Explanations

    ; followed by import

    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
    ansa
    -0.09
    antha
    -0.08
    ÏĦοÏį
    -0.08
    adra
    -0.08
    achel
    -0.08
    atonin
    -0.07
    -cache
    -0.07
     Vla
    -0.07
    anta
    -0.07
    eel
    -0.07
    POSITIVE LOGITS
    <|box_end|>
    0.07
    sky
    0.07
    DataStream
    0.06
    linky
    0.06
     |âĢ¢
    0.06
    请åħĪ
    0.06
    jø
    0.06
    !,
    0.06
    ky
    0.06
    ked
    0.06
    Activations Density 0.238%

    No Known Activations