© 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. 29113
    Prev
    Next
    INDEX
    Explanations

    against

    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
     Bail
    -0.28
     bail
    -0.27
    vider
    -0.25
    )$_
    -0.25
    too
    -0.25
    onna
    -0.25
    æ¯Ĺ
    -0.24
    æīĢæıIJä¾Ľä¹ĭ
    -0.24
     applaud
    -0.24
     quantities
    -0.24
    POSITIVE LOGITS
    eba
    0.29
    qui
    0.26
    è°Īè¯Ŀ
    0.24
    mart
    0.24
    mil
    0.24
    åı¯èĥ½åıijçĶŁ
    0.24
    ece
    0.24
     Convers
    0.24
     tick
    0.24
    icularly
    0.24
    Activations Density 0.301%

    No Known Activations