© 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. 41719
    Prev
    Next
    INDEX
    Explanations

    we

    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
    缸åħ³ä¿¡æģ¯
    -0.28
    RODUCTION
    -0.26
    ).</
    -0.25
    ulet
    -0.25
    éĥģ
    -0.24
    IVERY
    -0.24
    oten
    -0.24
    âĹ¢
    -0.24
    AGER
    -0.23
    eat
    -0.23
    POSITIVE LOGITS
    isch
    0.28
    esp
    0.27
    té
    0.26
    tá
    0.26
     Ta
    0.24
     Trick
    0.23
    achat
    0.23
    zeitig
    0.23
    esa
    0.23
     chap
    0.23
    Activations Density 0.239%

    No Known Activations