© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 39813
    Prev
    Next
    INDEX
    Explanations

    actually

    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
    Not in Any Lists

    No Comments

    Negative Logits
    resh
    -0.29
     accent
    -0.28
    atoria
    -0.28
    -Allow
    -0.25
    adera
    -0.25
    æľºåĬ¨
    -0.25
     pena
    -0.25
    icer
    -0.25
     face
    -0.24
    ADER
    -0.24
    POSITIVE LOGITS
    纸ä¸Ĭ
    0.25
    ToLocal
    0.25
    æĦĪ
    0.25
    åį¡çīĩ
    0.25
     shouted
    0.24
     orally
    0.24
    veau
    0.24
     kicks
    0.24
     expensive
    0.24
     kicked
    0.23
    Activations Density 2.337%

    No Known Activations