© 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. 39843
    Prev
    Next
    INDEX
    Explanations

    Mixed text/code/forum content

    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
    eping
    -0.27
     Saunders
    -0.26
    è¿Ħ
    -0.26
     IonicPage
    -0.26
     GÅĤ
    -0.25
    ä¸Ģå°ģä¿¡
    -0.24
    ãĤĴè¿İ
    -0.24
    mock
    -0.24
    ä¸Ģ缴åĪ°
    -0.24
     meis
    -0.24
    POSITIVE LOGITS
    oy
    0.29
    åĪ·
    0.27
    ense
    0.27
    ä¸ĢæĬĬ
    0.26
    undy
    0.25
    illis
    0.24
    åĬ¡
    0.24
     NONINFRINGEMENT
    0.24
    ÃĹ
    0.24
    竹
    0.24
    Activations Density 0.032%

    No Known Activations