© 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. 1887
    Prev
    Next
    INDEX
    Explanations

    synaptic

    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
    æĭīå¾·
    -0.09
    áng
    -0.07
    andet
    -0.07
    åĩºçĤī
    -0.07
    æĬľ
    -0.07
    .unshift
    -0.07
    ignet
    -0.07
    åħ´åĽ½
    -0.07
     unsub
    -0.07
     Tur
    -0.07
    POSITIVE LOGITS
     neurotrans
    0.11
    ç¥ŀç»ı
    0.10
     synaptic
    0.10
     neur
    0.08
     neu
    0.08
     neuron
    0.08
     Neuro
    0.08
    çĵ£
    0.08
     Neuroscience
    0.08
     neurons
    0.08
    Activations Density 0.060%

    No Known Activations