© 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. 14-TRANSCODER-HP
    7. 41716
    Prev
    Next
    INDEX
    Explanations

    diagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    hop
    -0.33
    å¼Ģ
    -0.31
    éĸĭ
    -0.27
    +)/
    -0.26
    eurs
    -0.26
     cir
    -0.26
    idable
    -0.25
    Hop
    -0.25
     duel
    -0.25
    .gov
    -0.24
    POSITIVE LOGITS
    Äı
    0.27
    .VALUE
    0.27
    象
    0.26
    å¿ĺãĤĮ
    0.25
    éĽģ
    0.24
    æĥħåĨµ
    0.24
    第ä¸Ģæī¹
    0.24
    esion
    0.24
    inkle
    0.23
     takeaway
    0.23
    Activations Density 0.262%

    No Known Activations