© 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. 95311
    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
    خرÙĪ
    -0.27
    ules
    -0.26
     ÑĦоÑĢ
    -0.25
    ä½Ĩä»ĸ
    -0.25
     scratches
    -0.25
    èµĦæľ¬
    -0.24
    åĪij
    -0.24
    ollection
    -0.24
     Rooney
    -0.24
    %X
    -0.23
    POSITIVE LOGITS
     WARRANTIES
    0.26
     Diss
    0.25
     ActiveForm
    0.25
    alık
    0.25
    èµ°åĬ¿åĽ¾
    0.24
    æĥķ
    0.24
    çİĩ为
    0.24
    pNet
    0.24
     ActiveSupport
    0.24
    otent
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.