© 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. 39806
    Prev
    Next
    INDEX
    Explanations

    Possibility/Ability

    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
    caption
    -0.27
    ç²¾
    -0.26
    imum
    -0.26
    bef
    -0.26
    azor
    -0.25
    å°±ä¸įä¼ļ
    -0.24
    endo
    -0.24
    å°ļ
    -0.24
    aneously
    -0.24
     meaning
    -0.23
    POSITIVE LOGITS
    缸åħ³æĶ¿çŃĸ
    0.25
    <H
    0.24
    "type
    0.24
    èĪĶ
    0.24
    æĹĹä¸ĭ
    0.24
    åIJ¬è¯Ŀ
    0.24
    <algorithm
    0.24
    \"",↵
    0.24
    <B
    0.23
     priorit
    0.23
    Activations Density 1.274%

    No Known Activations