© 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. 7017
    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
    ZONE
    -0.30
    LU
    -0.27
    Lu
    -0.27
    cf
    -0.27
    vel
    -0.26
    读åIJİ
    -0.26
    zone
    -0.26
    raid
    -0.24
     háºŃu
    -0.24
    lena
    -0.24
    POSITIVE LOGITS
    esian
    0.25
    unnel
    0.25
    urniture
    0.25
     listing
    0.25
     ì²ĺ
    0.24
    alink
    0.24
    icket
    0.23
    -required
    0.23
    .accept
    0.23
     insulting
    0.23
    Activations Density 0.131%

    No Known Activations

    This feature has no known activations.