© 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. 96104
    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
     ké
    -0.28
    hte
    -0.27
    fffffff
    -0.26
    à¸łà¸²à¸ŀ
    -0.24
    lé
    -0.24
    ãĥĽãĥ¼ãĥ«
    -0.24
    ãģ¤ãģª
    -0.24
    foot
    -0.23
     sobie
    -0.23
     Ow
    -0.23
    POSITIVE LOGITS
    cery
    0.28
     Exped
    0.26
    InSection
    0.25
    缸å¤Ħ
    0.24
    äºĴåĬ¨
    0.24
     trackers
    0.24
    àºĸ
    0.24
    iges
    0.24
    .format
    0.23
    ç»®
    0.23
    Activations Density 0.920%

    No Known Activations

    This feature has no known activations.