© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7447
    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
    èĢĥ
    -0.25
    ãģĻãģ¹ãģį
    -0.25
    ä¸į该
    -0.25
    rosse
    -0.25
     Buff
    -0.24
    max
    -0.24
    ace
    -0.24
    ramer
    -0.24
     IBM
    -0.24
    agogue
    -0.24
    POSITIVE LOGITS
    ì¤ijìķĻ
    0.28
    åŁĥå°Ķ
    0.27
    EI
    0.27
    arrings
    0.25
    udem
    0.25
    HEL
    0.24
     bored
    0.24
    Pel
    0.24
    elden
    0.24
    å¹³åĿĩæ¯ı
    0.24
    Activations Density 0.043%

    No Known Activations

    This feature has no known activations.