© 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. 25-TRANSCODER-HP
    7. 108879
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /tos
    -0.30
    xfc
    -0.29
     tor
    -0.27
    zed
    -0.25
     revelation
    -0.25
    riter
    -0.23
    Îĸ
    -0.23
     finals
    -0.23
    å®īåħ¨æĦŁ
    -0.23
    åĩºæĿ¥äºĨ
    -0.23
    POSITIVE LOGITS
    缼
    0.34
    hem
    0.29
     гоÑģ
    0.26
    hist
    0.25
    osite
    0.25
    ÑħоÑĤ
    0.25
    ainen
    0.23
    -prefix
    0.23
    вÑıз
    0.23
    éĺ¿æł¹
    0.23
    Activations Density 1.467%

    No Known Activations

    This feature has no known activations.