© 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. 27-TRANSCODER-HP
    7. 56999
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ió
    -0.24
     Cutter
    -0.24
     cams
    -0.23
     Lew
    -0.23
    .ActionBar
    -0.23
    è¢Ī
    -0.22
    _DESCRIPTION
    -0.22
     Shadows
    -0.22
    gewater
    -0.22
     kwargs
    -0.22
    POSITIVE LOGITS
    æĹłç§ģ
    0.26
    æĴŃæĬ¥
    0.26
    ·»
    0.26
    åľ°å¸¦
    0.25
    ulty
    0.23
    ä¹Łå¥½
    0.23
    ç»Ļåĩº
    0.23
    dep
    0.23
     incompetence
    0.23
    ynos
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.