© 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. 54006
    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
     Nab
    -0.25
    _Impl
    -0.25
    Executing
    -0.25
     dici
    -0.25
     positional
    -0.24
    åIJĦç§įåIJĦæł·
    -0.24
    çĥŃæIJľ
    -0.24
    -python
    -0.24
    _Version
    -0.24
     Germans
    -0.23
    POSITIVE LOGITS
    éĻ¤
    0.32
     Chick
    0.28
    æŃ»
    0.27
    é¢Ĥ
    0.25
     secure
    0.25
    aside
    0.25
    çĶŁæŃ»
    0.24
    æ¸ł
    0.24
    åĽŀ
    0.24
    owanie
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.