© 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. 17660
    Prev
    Next
    INDEX
    Explanations

    variable/field names

    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
    onos
    -0.08
    /member
    -0.07
    жÑĸ
    -0.07
     Knob
    -0.07
    娱
    -0.07
     /></
    -0.07
    æĺķ
    -0.07
     mengen
    -0.07
    åıĸç·ł
    -0.07
    òng
    -0.07
    POSITIVE LOGITS
    arness
    0.08
    estro
    0.07
    pecific
    0.07
    ihak
    0.06
     el
    0.06
    edata
    0.06
    ë³Ħ
    0.06
     sc
    0.06
    enheim
    0.06
    ValuePair
    0.06
    Activations Density 0.089%

    No Known Activations