© 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. 39942
    Prev
    Next
    INDEX
    Explanations

    scientific research articles

    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
     recounts
    -0.25
     recount
    -0.25
    æİĮæı¡
    -0.24
    linewidth
    -0.24
    -FIRST
    -0.23
    è¾Ĥ
    -0.23
    读æĩĤ
    -0.23
    -popup
    -0.23
    atched
    -0.23
    em
    -0.23
    POSITIVE LOGITS
    åħ¶ä¸Ńæľī
    0.30
    鸢
    0.27
    Wnd
    0.25
    Evaluator
    0.25
     favoured
    0.24
    缮
    0.24
     EDM
    0.24
    inherits
    0.24
    spl
    0.24
    Vars
    0.23
    Activations Density 0.915%

    No Known Activations