© 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. 20-TRANSCODER-HP
    7. 129828
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĴ¨
    -0.29
    ä»İäºĭ
    -0.28
    .aw
    -0.26
     person
    -0.24
    person
    -0.24
    ansom
    -0.24
    alto
    -0.24
    å¸ħ
    -0.24
    ãĤº
    -0.23
    _subtype
    -0.23
    POSITIVE LOGITS
    verbatim
    0.25
    éĻIJ
    0.24
     Clim
    0.24
    ï¹ģ
    0.23
    orrent
    0.23
    éĿŀ常æĺİæĺ¾
    0.23
    åħĪè¡Į
    0.23
    Const
    0.23
     serge
    0.23
     Const
    0.23
    Activations Density 0.751%

    No Known Activations

    This feature has no known activations.