© 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. 12-TRANSCODER-HP
    7. 24257
    Prev
    Next
    INDEX
    Explanations

    Attempts, trying, to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸Ģçľĭ
    -0.28
    åıĹä¸įäºĨ
    -0.27
    lemen
    -0.27
    åıĭ好
    -0.26
     attempting
    -0.25
    åľ¨æѤ
    -0.24
    åı¯æĥ³èĢĮçŁ¥
    -0.24
    sembly
    -0.24
     Chart
    -0.24
    å°Ŀè¯ķ
    -0.24
    POSITIVE LOGITS
    é¾Ł
    0.27
    unda
    0.27
    gee
    0.26
     trunc
    0.26
    追
    0.26
    shirt
    0.25
     sal
    0.25
    osphere
    0.24
    çĶ°
    0.24
    åĬ³åĬ¨
    0.24
    Activations Density 0.009%

    No Known Activations