© 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. 96315
    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
    éľĩæĥĬ
    -0.27
    çĺ¿
    -0.26
    inka
    -0.25
    /rem
    -0.25
    avad
    -0.25
    pond
    -0.25
    CACHE
    -0.25
    nuts
    -0.25
    enaries
    -0.25
     tread
    -0.24
    POSITIVE LOGITS
     ass
    0.30
    borg
    0.29
    éķ¿å¤§
    0.26
    Leod
    0.26
    /screen
    0.26
    èĽİ
    0.25
    iga
    0.25
    å¾ĢåIJİ
    0.25
    éĢı
    0.23
    大大å°ı
    0.23
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.