© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23491
    Prev
    Next
    INDEX
    Explanations

    standard output functions

    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
    ikum
    -0.07
    纪åħĥ
    -0.07
    laut
    -0.07
    klik
    -0.07
    åľ¨åİ¿
    -0.07
    jur
    -0.07
     szen
    -0.07
    æŀķ
    -0.06
    anax
    -0.06
    obr
    -0.06
    POSITIVE LOGITS
    uttle
    0.07
    åĵŃäºĨ
    0.07
    arf
    0.07
    δÎŃ
    0.06
    æ·«
    0.06
    andon
    0.06
    รม
    0.06
    fels
    0.06
    ORY
    0.06
    ornado
    0.06
    Activations Density 0.002%

    No Known Activations