© 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. 41548
    Prev
    Next
    INDEX
    Explanations

    article

    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
    æİĴåºı
    -0.26
    ãģ¶
    -0.26
    åĪĬ
    -0.25
    Getter
    -0.25
     zab
    -0.24
    centage
    -0.24
     fret
    -0.24
    çĸı
    -0.24
    æĸ·
    -0.24
    åĽłä¸ºå¥¹
    -0.24
    POSITIVE LOGITS
    edes
    0.26
    éĢĥ
    0.24
    éĢĨ转
    0.23
    Vir
    0.23
    vos
    0.23
     camel
    0.23
    Extend
    0.23
    身
    0.23
    inherits
    0.23
    alen
    0.23
    Activations Density 0.321%

    No Known Activations