© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130514
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ycz
    -0.24
     balance
    -0.22
    å¾Ĺèµ·
    -0.22
     geographical
    -0.22
    ULE
    -0.22
    ochond
    -0.22
    uellement
    -0.22
    <!--[
    -0.21
    äll
    -0.21
    lien
    -0.21
    POSITIVE LOGITS
    çĶ¨çĶµ
    0.23
    sites
    0.22
    iped
    0.22
    å¦Ļ
    0.22
    irling
    0.22
    æĿŁ
    0.22
    ointed
    0.21
    MediaType
    0.21
     Plasma
    0.21
    automation
    0.21
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.