© 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. 96496
    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
    æŃ£åľ¨
    -0.28
     pitch
    -0.26
     DeepCopy
    -0.25
    åIJĥé¥Ń
    -0.25
    ä¸ĭéĿ¢æĺ¯
    -0.25
     Chains
    -0.25
    é«ĺ度
    -0.25
    ç¨ĭ
    -0.25
    ek
    -0.24
    (Index
    -0.24
    POSITIVE LOGITS
    ãĥ¼ãĤ¹
    0.26
    anging
    0.25
    añ
    0.25
    å°ijäºĨ
    0.25
     Bron
    0.25
     af
    0.25
     shrinking
    0.25
    amework
    0.24
    æĮ«
    0.24
    SQLException
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.