© 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. 22-TRANSCODER-HP
    7. 99222
    Prev
    Next
    INDEX
    Explanations

    -producing, -ating, -ing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĻĤ
    -0.26
    otec
    -0.24
    ãģıãĤĮ
    -0.24
    bung
    -0.24
    mie
    -0.23
    bre
    -0.23
    tap
    -0.23
    avel
    -0.23
    -guide
    -0.23
     tapping
    -0.23
    POSITIVE LOGITS
    ody
    0.30
    éħ·
    0.28
    aye
    0.27
    ä¸Ģæł·çļĦ
    0.25
    odu
    0.24
    yz
    0.24
     casc
    0.24
    Ord
    0.23
     ny
    0.23
    getic
    0.23
    Activations Density 0.043%

    No Known Activations