© 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. 58130
    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
    apol
    -0.31
     setId
    -0.30
    ä¸Ģæīĭ
    -0.26
    ableView
    -0.25
    abol
    -0.25
    æ°´ä¸Ĭ
    -0.24
     MART
    -0.24
    -win
    -0.24
    ROL
    -0.24
     Ide
    -0.23
    POSITIVE LOGITS
     Deals
    0.27
     thừa
    0.26
    ire
    0.25
    é¬ĺ
    0.25
    è¦ģä¹Ī
    0.25
    .cgi
    0.25
    ä¼łçľŁ
    0.25
    åīįåı°
    0.24
    é¦ģ
    0.24
    Mad
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.