© 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. 39574
    Prev
    Next
    INDEX
    Explanations

    check

    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
    ä¼´
    -0.29
    身åIJİ
    -0.27
    GM
    -0.27
    çĮ®
    -0.27
    -commit
    -0.26
    ResourceManager
    -0.25
    ()][
    -0.25
     lives
    -0.24
    .decor
    -0.24
     Lives
    -0.24
    POSITIVE LOGITS
    alore
    0.34
    Derived
    0.26
    marked
    0.26
    -ed
    0.26
    иÑĦика
    0.25
    emark
    0.25
    红èī²
    0.24
    ierung
    0.24
    ede
    0.23
     raspberry
    0.23
    Activations Density 0.678%

    No Known Activations