© 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. 8319
    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
    æģº
    -0.28
    aceous
    -0.27
    atform
    -0.27
    erate
    -0.25
     concurrently
    -0.25
     inert
    -0.25
    wer
    -0.24
    åħļåĴĮåĽ½å®¶
    -0.24
     Equ
    -0.24
    ì¹ĺ
    -0.24
    POSITIVE LOGITS
    åİļåİļ
    0.27
    hoot
    0.25
     offsetX
    0.25
    ÑĪиÑĢ
    0.24
    exact
    0.24
    ÙĦÙĬÙģ
    0.24
    åĨįæĿ¥
    0.24
    ãĥĽ
    0.24
     *[
    0.24
    )[-
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.