© 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. 39979
    Prev
    Next
    INDEX
    Explanations

    professor or java

    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
     stripes
    -0.25
     implied
    -0.24
    并å°Ĩ
    -0.24
    ç£ķ
    -0.24
    çļĦæķĻåѦ
    -0.24
     park
    -0.23
     observations
    -0.23
    æ°ijå¿ĥ
    -0.23
    æŃ¥
    -0.23
     Blo
    -0.23
    POSITIVE LOGITS
    ubs
    0.28
    ucker
    0.27
    åĬłå¿«å»ºè®¾
    0.25
    èĥł
    0.25
    oba
    0.25
    zc
    0.25
    串
    0.25
    ä¹³
    0.24
    neh
    0.24
    ogl
    0.23
    Activations Density 0.094%

    No Known Activations