© 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. 19-TRANSCODER-HP
    7. 8247
    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
    楸
    -0.32
    exercise
    -0.25
     Ad
    -0.25
    ä¸įä¸Ģå®ļ
    -0.25
     Bihar
    -0.25
    AMPLE
    -0.24
    lim
    -0.24
    ç¤ģ
    -0.24
     Cly
    -0.23
     derby
    -0.23
    POSITIVE LOGITS
    ŀĭ
    0.28
    ấu
    0.26
    parable
    0.26
    munition
    0.25
    åĩºçĶŁ
    0.24
    tributes
    0.24
    atype
    0.23
    """),↵
    0.23
     speech
    0.23
    uito
    0.23
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.