© 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. 12108
    Prev
    Next
    INDEX
    Explanations

    made available

    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
    odka
    -0.09
    medio
    -0.09
    unno
    -0.09
    æ°ĵ
    -0.09
    SHOT
    -0.09
    ampir
    -0.08
    Ñģкоп
    -0.08
    repid
    -0.08
    неÑĤÑĥ
    -0.08
    byname
    -0.08
    POSITIVE LOGITS
    leine
    0.13
     sure
    0.12
    intosh
    0.11
    erv
    0.09
    fulness
    0.09
     havoc
    0.09
    fully
    0.09
    hift
    0.08
    eted
    0.08
    ifest
    0.08
    Activations Density 0.198%

    No Known Activations