© 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. 9275
    Prev
    Next
    INDEX
    Explanations

    objectclass

    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
    rato
    -0.06
    arang
    -0.06
     opp
    -0.06
     Tape
    -0.06
    çļĦçī¹æĢ§
    -0.06
     acquis
    -0.06
    L
    -0.06
    æĹłæķħ
    -0.06
    è¿Ļä¸ªä¸ľè¥¿
    -0.06
    æĥ³çĿĢ
    -0.06
    POSITIVE LOGITS
    mium
    0.09
     Ejem
    0.08
    ithe
    0.08
    ÃŃv
    0.07
    (#)
    0.07
    "./
    0.07
    deaux
    0.07
    xima
    0.07
    benh
    0.07
    ihal
    0.07
    Activations Density 0.026%

    No Known Activations