© 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. 22087
    Prev
    Next
    INDEX
    Explanations

    Web page snippets

    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
    代çIJĨ
    -0.32
    æĤĮ
    -0.30
    enson
    -0.28
    ugging
    -0.27
    agent
    -0.27
    çijĽ
    -0.27
    ddy
    -0.26
     psychologically
    -0.25
    ires
    -0.23
     doll
    -0.23
    POSITIVE LOGITS
    adoras
    0.28
     cou
    0.28
    uids
    0.27
    æīĪ
    0.27
    |required
    0.27
    icontrol
    0.26
    clidean
    0.26
    quals
    0.26
    竦
    0.26
    çŃ·åŃIJ
    0.24
    Activations Density 0.014%

    No Known Activations