© 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. 54357
    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
    (||
    -0.29
    _ALIAS
    -0.25
    ChangedEventArgs
    -0.24
    éĺĸ
    -0.24
    iego
    -0.24
    輩
    -0.24
    cams
    -0.24
    ORB
    -0.24
    GENCY
    -0.23
    izens
    -0.23
    POSITIVE LOGITS
    èĢĮæĿ¥
    0.26
    ottes
    0.26
    ое
    0.25
    R
    0.24
    é£
    0.24
     vain
    0.23
    DMI
    0.23
    èĢĮåİ»
    0.23
     Spin
    0.23
    赤
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.