© 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. 39838
    Prev
    Next
    INDEX
    Explanations

    Code and file contents

    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
    ç»Ļä½łä»¬
    -0.27
    emu
    -0.26
    è§ĦåĪĻ
    -0.26
     pel
    -0.25
    yo
    -0.24
    HING
    -0.24
     Controls
    -0.24
    -br
    -0.24
    -tra
    -0.24
    hive
    -0.24
    POSITIVE LOGITS
     Afro
    0.25
    Away
    0.24
     stead
    0.23
     clicks
    0.23
     ÑģÑĤоим
    0.23
    请éĢīæĭ©
    0.22
    çŀij
    0.22
     IDEA
    0.22
    -away
    0.21
    åıijå±ķä¸Ń
    0.21
    Activations Density 0.921%

    No Known Activations