© 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. 8769
    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
    unta
    -0.29
    akis
    -0.26
    å¾Ģåīį
    -0.26
    _solution
    -0.25
    quo
    -0.25
     Dak
    -0.24
    æĮ¯
    -0.24
    ãģ¶
    -0.24
    çŃīå¾ħ
    -0.24
    认
    -0.23
    POSITIVE LOGITS
    ä¸ŃåĽ½æĸĩåĮĸ
    0.27
    clar
    0.25
     supers
    0.25
    stände
    0.25
    å°º
    0.25
     McD
    0.25
    oji
    0.25
    ä¸ŃåĽ½åĪ¶éĢł
    0.25
    notin
    0.25
    -space
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.