© 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. 39421
    Prev
    Next
    INDEX
    Explanations

    study/question

    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
    æ°¨éħ¸
    -0.29
    gv
    -0.28
    _receive
    -0.27
     priced
    -0.27
     receptions
    -0.27
    ä¸ĭè¾¾
    -0.26
     prosper
    -0.26
    oders
    -0.26
    ết
    -0.26
    çĶŁæĢķ
    -0.26
    POSITIVE LOGITS
    éŨæĪ·
    0.28
    _tri
    0.25
    vere
    0.25
    portfolio
    0.24
    onica
    0.24
    ported
    0.24
     deck
    0.24
    <HTML
    0.23
    akest
    0.23
     biggest
    0.23
    Activations Density 1.770%

    No Known Activations