© 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. 40345
    Prev
    Next
    INDEX
    Explanations

    fluids

    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
    ä¸į容æĺĵ
    -0.27
     %↵↵
    -0.25
    ilyn
    -0.25
     (!((
    -0.24
    Ł³
    -0.24
    奸
    -0.24
     tin
    -0.24
    ç«Ļ
    -0.24
    çħ¤
    -0.23
    unky
    -0.23
    POSITIVE LOGITS
    oit
    0.27
    åħļåĴĮ
    0.27
    çİ
    0.26
     professionalism
    0.25
    ().__
    0.25
    森æŀĹåħ¬åĽŃ
    0.25
    æīĵçIJĥ
    0.24
    phe
    0.24
    ething
    0.24
    asil
    0.23
    Activations Density 0.107%

    No Known Activations