© 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. 39589
    Prev
    Next
    INDEX
    Explanations

    UK

    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
     fog
    -0.30
    éľ
    -0.26
     Fog
    -0.25
     Quincy
    -0.25
    ä½ľèĢħæľ¬äºº
    -0.24
    .psi
    -0.24
    ffa
    -0.24
    imus
    -0.24
    _BODY
    -0.24
    .constraint
    -0.24
    POSITIVE LOGITS
    esome
    0.27
     harmless
    0.26
    them
    0.26
    触
    0.25
     dig
    0.25
    ZA
    0.25
    aked
    0.24
    产çĶŁçļĦ
    0.24
    sticks
    0.24
    lan
    0.24
    Activations Density 0.340%

    No Known Activations