© 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. 9027
    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
     rec
    -0.28
     nd
    -0.28
    è¿Ľåº¦
    -0.27
    'd
    -0.26
     ed
    -0.26
    gel
    -0.25
    "
    -0.25
     count
    -0.24
    款
    -0.24
     forest
    -0.24
    POSITIVE LOGITS
    ahoo
    0.30
    å½±åĵįåĬĽçļĦ
    0.28
    drs
    0.28
    è·ijäºĨ
    0.27
    anta
    0.26
     Vy
    0.26
    UNCH
    0.26
    RunWith
    0.26
    zos
    0.26
     promoters
    0.25
    Activations Density 0.702%

    No Known Activations

    This feature has no known activations.