© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29135
    Prev
    Next
    INDEX
    Explanations

    Non-English text or code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ¯Ķè¾ĥ
    -0.29
    deny
    -0.27
    ä¸ĭåİ»
    -0.27
    ä¸Ģåı£æ°Ķ
    -0.27
    份
    -0.26
    {}_
    -0.26
    tps
    -0.26
    aler
    -0.26
    tp
    -0.25
    tower
    -0.25
    POSITIVE LOGITS
    磺
    0.29
    Ether
    0.28
    Mutable
    0.28
    毯
    0.27
     til
    0.27
    æīģ
    0.27
     rather
    0.26
    éĸĵéģķãģĦ
    0.25
     snapped
    0.24
    Evidence
    0.24
    Activations Density 6.795%

    No Known Activations