© 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. 41653
    Prev
    Next
    INDEX
    Explanations

    Pressure

    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
    ä¸Ģå¥Ĺ
    -0.31
    LEE
    -0.30
     lacking
    -0.25
    -opacity
    -0.25
    lé
    -0.25
     Leakage
    -0.25
    jective
    -0.24
    hyp
    -0.24
     catering
    -0.24
    浦
    -0.24
    POSITIVE LOGITS
    illes
    0.27
    xfd
    0.26
    etros
    0.25
    uckle
    0.25
    .todos
    0.25
     Cock
    0.24
    stk
    0.24
    dna
    0.24
     Occupy
    0.23
    oms
    0.23
    Activations Density 1.124%

    No Known Activations