© 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. 39551
    Prev
    Next
    INDEX
    Explanations

    Quantitative data

    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
     ImmutableList
    -0.28
    OrDefault
    -0.28
    à¤
    -0.27
     Emirates
    -0.26
     Immutable
    -0.26
    åľ°çľĭçĿĢ
    -0.26
    é«ĺåľ°
    -0.25
    Welcome
    -0.25
    çĽ¼
    -0.25
    èľļ
    -0.25
    POSITIVE LOGITS
    лик
    0.31
    lichkeit
    0.27
    碧
    0.27
    ikal
    0.27
    *time
    0.25
    adoo
    0.25
    isman
    0.25
    лин
    0.24
    å®ī举
    0.24
    inge
    0.24
    Activations Density 1.097%

    No Known Activations