© 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. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 39877
    Prev
    Next
    INDEX
    Explanations

    migraine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -ajax
    -0.27
     backlog
    -0.27
    less
    -0.25
    央ä¼ģ
    -0.24
    æĮģèĤ¡
    -0.24
    compan
    -0.24
    äge
    -0.23
    -span
    -0.23
     kilomet
    -0.23
    oring
    -0.23
    POSITIVE LOGITS
     INF
    0.27
    æĭIJ
    0.27
    oscope
    0.27
    opher
    0.27
     DECL
    0.26
    é»Ħèī²
    0.26
    Bi
    0.26
    åĽ¾æĸĩ
    0.25
    DISABLE
    0.25
     yellow
    0.24
    Activations Density 0.202%

    No Known Activations