© 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. 40102
    Prev
    Next
    INDEX
    Explanations

    guidance

    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
    åijĬè¯ī她
    -0.30
    ç¼®
    -0.25
    æĸ¯é¡¿
    -0.24
    (compact
    -0.23
     Jab
    -0.23
    ç»Ļ她
    -0.23
    Deposit
    -0.23
     userDetails
    -0.23
    forcing
    -0.23
     closet
    -0.23
    POSITIVE LOGITS
    åIJĥçļĦ
    0.26
    erie
    0.26
     fres
    0.26
    表éĿ¢ä¸Ĭ
    0.26
    uite
    0.26
    åIJĥ
    0.25
    ERA
    0.25
    ülü
    0.24
    å¤ĩ
    0.24
     createStore
    0.23
    Activations Density 0.844%

    No Known Activations