© 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. 18-TRANSCODER-HP
    7. 89094
    Prev
    Next
    INDEX
    Explanations

    Vague, economics/health/science vocab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¬
    -0.30
    shr
    -0.28
    é¢Ħè¨Ģ
    -0.26
     turning
    -0.24
    DataContract
    -0.24
    casts
    -0.24
    ports
    -0.24
    vard
    -0.23
    iable
    -0.23
    DBC
    -0.23
    POSITIVE LOGITS
    æĵį
    0.28
     bif
    0.26
    çķĢ
    0.26
    аж
    0.25
     succ
    0.24
    eel
    0.24
    éĥ¨éĥ¨éķ¿
    0.24
    ä¸įæħİ
    0.24
    ~~
    0.23
    ee
    0.23
    Activations Density 25.916%

    No Known Activations