© 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. 33-TRANSCODER-HP
    7. 53241
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITTER
    -0.29
    ?v
    -0.28
    oru
    -0.27
    <M
    -0.26
    ATAR
    -0.25
    attles
    -0.25
    <J
    -0.25
    ;charset
    -0.25
     ozone
    -0.24
    ’B
    -0.24
    POSITIVE LOGITS
     _
    0.32
     first
    0.31
    first
    0.29
    ä¼ļ使
    0.28
    åĨĻäºĨ
    0.28
    第ä¸Ģ
    0.27
     hatch
    0.27
    第ä¸ĢèĬĤ
    0.26
    prec
    0.26
     matures
    0.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.