© 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. 22062
    Prev
    Next
    INDEX
    Explanations

    Inheritance and succession

    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
    æĹĮ
    -0.28
     bz
    -0.27
    inges
    -0.26
    ocard
    -0.25
     Separate
    -0.25
     Separ
    -0.24
     pareja
    -0.24
     scrap
    -0.24
    ãĥijãĥ¼ãĥĪ
    -0.24
    .bp
    -0.24
    POSITIVE LOGITS
    赶
    0.28
    å±Ĥå±Ĥ
    0.27
    åĨľ
    0.25
    åIJ«
    0.25
    éĴ»
    0.25
    æįķ
    0.25
    hole
    0.24
    |-
    0.24
    å®Ī
    0.24
    MPI
    0.24
    Activations Density 0.001%

    No Known Activations