© 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. 88188
    Prev
    Next
    INDEX
    Explanations

    and, comma

    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
    æĪijå¿ĥéĩĮ
    -0.30
    onas
    -0.30
    ëĤ©
    -0.27
    hti
    -0.26
    éĢ¼
    -0.25
    fastcall
    -0.25
    人éĹ´
    -0.25
     refin
    -0.24
    .Align
    -0.23
    çĥĤ
    -0.23
    POSITIVE LOGITS
    麹
    0.27
    atron
    0.27
    ographies
    0.27
    ãģĮãĤī
    0.25
    eel
    0.25
    ableObject
    0.25
    æ»ŀ
    0.25
    anner
    0.24
    egral
    0.24
    ataire
    0.24
    Activations Density 15.218%

    No Known Activations