© 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. 27-TRANSCODER-HP
    7. 9893
    Prev
    Next
    INDEX
    Explanations

    say the ending -ological/-ometric

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    串
    -0.29
    çĽ
    -0.28
    顶
    -0.27
    顶éĥ¨
    -0.27
    vic
    -0.26
    atas
    -0.25
     top
    -0.25
    naire
    -0.25
     monitor
    -0.24
    kke
    -0.24
    POSITIVE LOGITS
    alte
    0.29
    eness
    0.27
    sar
    0.27
    sav
    0.26
    desired
    0.26
     ning
    0.26
    imentary
    0.26
    eful
    0.26
    Annotations
    0.26
    çĦ¶
    0.25
    Activations Density 1.007%

    No Known Activations