© 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. 20-TRANSCODER-HP
    7. 141622
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĿ³
    -0.30
    åĮ¡
    -0.27
    -pane
    -0.25
     unicode
    -0.25
    ArrayOf
    -0.25
    èĻº
    -0.24
    åĿ¦
    -0.24
     nghá»ĭ
    -0.24
    éħĴåºĹ
    -0.24
    缴å¾Ħ
    -0.23
    POSITIVE LOGITS
     wed
    0.27
    cret
    0.25
     melts
    0.24
    MED
    0.24
    ëĨĢ
    0.24
    ES
    0.24
    Med
    0.24
    å®Į
    0.24
     facts
    0.23
    ESH
    0.23
    Activations Density 12.518%

    No Known Activations

    This feature has no known activations.