© 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. 7854
    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
     bus
    -0.26
    sun
    -0.26
    樾
    -0.25
     intern
    -0.25
    /exec
    -0.25
    æī§
    -0.24
    sport
    -0.24
    çĽij
    -0.24
     Dr
    -0.24
    sse
    -0.24
    POSITIVE LOGITS
    imdi
    0.29
     IDM
    0.28
    MSN
    0.26
    å°Ķ
    0.26
    -Smith
    0.26
    ifers
    0.25
    (KP
    0.24
     dow
    0.24
     crib
    0.24
     Bookmark
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.