© 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. 39523
    Prev
    Next
    INDEX
    Explanations

    Code/file summaries

    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
    yat
    -0.29
    ADING
    -0.26
    æĬ½
    -0.26
    aturated
    -0.25
    udem
    -0.25
    çĶļèĩ³
    -0.25
    istar
    -0.25
    åĢĻ
    -0.24
     ?>&
    -0.24
     SPDX
    -0.24
    POSITIVE LOGITS
    Sym
    0.25
     gaps
    0.25
    вл
    0.25
    :http
    0.25
     responders
    0.24
    ä¸Ģéģĵ
    0.24
     téc
    0.24
    ä¸Ģä¼ļ
    0.24
    segments
    0.23
    plex
    0.23
    Activations Density 0.289%

    No Known Activations