© 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. 58052
    Prev
    Next
    INDEX
    Explanations

    legal citations ending in Rptr

    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
    ellar
    -0.07
    leine
    -0.07
    jek
    -0.07
    patrick
    -0.07
    ettle
    -0.06
    hung
    -0.06
    ajan
    -0.06
    quier
    -0.06
    åĭĥåĭĥ
    -0.06
    udian
    -0.06
    POSITIVE LOGITS
    enek
    0.08
    enin
    0.08
    imbledon
    0.08
    agt
    0.08
    amin
    0.08
    amburger
    0.08
    ØŃاب
    0.07
     Crosby
    0.07
    arks
    0.07
    msp
    0.07
    Activations Density 0.694%

    No Known Activations