© 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. 95569
    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
    .words
    -0.28
    поÑĢ
    -0.26
    ounces
    -0.26
    åıĮè¾¹
    -0.26
    港åı£
    -0.25
    æĭ¥æĬ¤
    -0.25
    /support
    -0.25
    ynom
    -0.25
    umb
    -0.25
    ÙĪÙĦÙĬ
    -0.25
    POSITIVE LOGITS
    RACT
    0.27
    .HandleFunc
    0.26
    .GetObject
    0.26
     lact
    0.26
    缦
    0.25
     Tra
    0.25
    é¢Ĩ导
    0.25
    icot
    0.25
    è¶Ĭ
    0.25
     Leader
    0.25
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.