© 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. 30-TRANSCODER-HP
    7. 96425
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opt
    -0.27
    éĢĢè¿ĺ
    -0.27
    -caption
    -0.26
     thanking
    -0.25
    Toolkit
    -0.25
    optic
    -0.25
     ink
    -0.24
    len
    -0.24
     Torch
    -0.23
    OPT
    -0.23
    POSITIVE LOGITS
    å°ıæŶ
    0.29
    pez
    0.27
     mixer
    0.27
    -www
    0.26
    arer
    0.26
    çĪ¬
    0.25
     bursting
    0.25
    erez
    0.25
    lichkeit
    0.24
    .subplots
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.