© 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. 18-TRANSCODER-HP
    7. 90349
    Prev
    Next
    INDEX
    Explanations

    Village

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    odyn
    -0.28
    -offset
    -0.28
     offset
    -0.27
    èĥ½çľĭåĪ°
    -0.26
    çĶ©
    -0.26
    âĪ
    -0.26
    åģıåIJij
    -0.25
    _IMPORTED
    -0.25
    ultipart
    -0.25
    çľĭè§ģ
    -0.25
    POSITIVE LOGITS
    AIM
    0.28
    +t
    0.28
     Zo
    0.27
    mania
    0.27
    eri
    0.26
    ÙħÙĩ
    0.26
    edo
    0.26
    ifacts
    0.25
    esz
    0.25
     AIM
    0.25
    Activations Density 65.528%

    No Known Activations