© 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. 24130
    Prev
    Next
    INDEX
    Explanations

    soil

    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
    æĭ¥
    -0.28
    éļħ
    -0.26
    çĿĢæīĭ
    -0.26
     binnen
    -0.25
     Virgin
    -0.25
     bursts
    -0.25
    -period
    -0.25
    è¾ĺ
    -0.25
    .Listen
    -0.25
     empirical
    -0.24
    POSITIVE LOGITS
    αι
    0.26
    è¦ģä¸įè¦ģ
    0.26
    /ion
    0.26
    ankind
    0.25
    ption
    0.25
     congratulations
    0.25
    enville
    0.24
     BELOW
    0.24
    xfe
    0.24
    tc
    0.23
    Activations Density 0.001%

    No Known Activations