© 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. 60736
    Prev
    Next
    INDEX
    Explanations

    lamina, layered, layers, stacked

    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
    ihu
    -0.09
    ambi
    -0.08
    çĸĨ
    -0.08
    çķĶ
    -0.08
    ecke
    -0.07
    åĪ°å¤Ħ
    -0.07
    Bone
    -0.07
    iato
    -0.07
    çĭŀ
    -0.07
    èĶĵ
    -0.07
    POSITIVE LOGITS
     layers
    0.18
     Layers
    0.15
    å±Ĥ
    0.15
     layer
    0.14
    layers
    0.14
    å±Ĥå±Ĥ
    0.14
    å±ĤçļĦ
    0.14
     layered
    0.14
    Layers
    0.14
    層
    0.14
    Activations Density 0.080%

    No Known Activations