© 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. 15221
    Prev
    Next
    INDEX
    Explanations

    make sure

    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
    undry
    -0.08
    åĬ¨è¾Ħ
    -0.08
    voirs
    -0.08
    utorial
    -0.07
    ottie
    -0.07
    osomal
    -0.07
    anyak
    -0.07
    udad
    -0.07
    常说çļĦ
    -0.07
    WARDS
    -0.07
    POSITIVE LOGITS
    à¹ģà¸Ļà¹Īà¹ĥà¸Ī
    0.10
     sure
    0.09
    注æĦıçļĦæĺ¯
    0.07
    pared
    0.07
    ity
    0.07
    stab
    0.06
    ä¸Ģä¸ĭ
    0.06
    çľĭåĩº
    0.06
    же
    0.06
    åĢĭ
    0.06
    Activations Density 0.031%

    No Known Activations