© 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. 7157
    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
    æĮĩå®ļ
    -0.30
    ãģĭãģijãģ¦
    -0.26
    -sign
    -0.26
    éĹ»
    -0.25
     dissip
    -0.24
    -ng
    -0.24
    ir
    -0.24
    饮
    -0.24
    ient
    -0.23
    ager
    -0.23
    POSITIVE LOGITS
    alink
    0.31
    OURCE
    0.29
     titre
    0.28
    [Index
    0.28
    éĩį温
    0.27
    ç®ĹäºĨ
    0.26
    æ¸Ĭ
    0.26
    getic
    0.25
    oho
    0.25
    åįĹè·¯
    0.24
    Activations Density 0.029%

    No Known Activations

    This feature has no known activations.