© 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. 54298
    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
     mass
    -0.27
    rä
    -0.26
    anzi
    -0.26
    rz
    -0.25
    OI
    -0.25
    @endsection
    -0.25
     Bard
    -0.25
    RP
    -0.24
    riz
    -0.24
    好åIJĥ
    -0.24
    POSITIVE LOGITS
     Islamabad
    0.27
    emes
    0.27
    epam
    0.26
    SFML
    0.26
    elves
    0.26
    INTERNAL
    0.25
    ighbor
    0.24
    å·´åŁº
    0.24
    çļĦåİŁåĪĻ
    0.24
    oker
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.