© 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. 6970
    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
    akedown
    -0.28
     Builder
    -0.27
    mdir
    -0.24
    æŬ
    -0.23
    '",
    -0.23
    udas
    -0.23
    iston
    -0.23
    ikut
    -0.23
    inas
    -0.23
    INCREMENT
    -0.23
    POSITIVE LOGITS
    dea
    0.28
    æĹĦ
    0.26
    éĩĮ
    0.25
    ä¸Ńè¶ħ
    0.25
    èĪį
    0.24
    lems
    0.24
    好ä¸į容æĺĵ
    0.24
    ARNING
    0.24
     ['',
    0.24
    _questions
    0.24
    Activations Density 0.076%

    No Known Activations

    This feature has no known activations.