© 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. 7960
    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
    wal
    -0.28
    ongoose
    -0.27
    velopment
    -0.25
    łģ
    -0.24
    fone
    -0.23
    çĶŁçĶŁ
    -0.23
    æīĭ表
    -0.23
     GPL
    -0.23
    饰
    -0.23
    utow
    -0.23
    POSITIVE LOGITS
    å¢ŀéĩı
    0.25
    ç´¯äºĨ
    0.25
    ye
    0.25
    suite
    0.24
    ADV
    0.24
    -pos
    0.24
    igers
    0.23
     +:+
    0.23
     cut
    0.23
    jah
    0.23
    Activations Density 0.084%

    No Known Activations

    This feature has no known activations.