© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4863
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arth
    -0.28
    _LICENSE
    -0.28
    éķ¿å¾Ĺ
    -0.27
    该éĻ¢
    -0.26
    anford
    -0.26
    /licenses
    -0.25
    çļĦä¸Ģéĥ¨åĪĨ
    -0.25
     aras
    -0.24
    aptor
    -0.24
    ç®Ģä»ĭ
    -0.24
    POSITIVE LOGITS
    _AG
    0.27
    ìħĶ
    0.26
    ensed
    0.25
     sock
    0.24
    ums
    0.24
    åĴ³
    0.24
    rolled
    0.24
    URED
    0.24
     rolls
    0.24
    ä¹ŀ
    0.23
    Activations Density 1.100%

    No Known Activations

    This feature has no known activations.