© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 41749
    Prev
    Next
    INDEX
    Explanations

    Technical text with code snippets

    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
    Negative Logits
    Enlarge
    -0.27
    eling
    -0.26
    客åķĨ
    -0.25
    è¡Įäºĭ
    -0.25
    anking
    -0.25
     nämlich
    -0.24
    èĢĥä¸Ĭ
    -0.24
    _death
    -0.23
    çľĭä»ĸ
    -0.23
    BSD
    -0.23
    POSITIVE LOGITS
    json
    0.29
    angan
    0.28
     JSON
    0.27
    æĪijåıijçİ°
    0.27
     json
    0.27
    éĴ¢çIJ´
    0.26
     anywhere
    0.26
    _ws
    0.25
    éļıæľº
    0.24
    è½½
    0.24
    Activations Density 0.448%

    No Known Activations