© 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. 112889
    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
    大家åĪĨ享
    -0.27
    il
    -0.27
    ä½ľèĢħ
    -0.24
    æĭŁ
    -0.23
    [System
    -0.23
    (py
    -0.23
    ennes
    -0.23
    åĪĨ彩
    -0.23
    Hostname
    -0.22
    å°ıç¼ĸ
    -0.22
    POSITIVE LOGITS
    legation
    0.25
    agara
    0.25
    stations
    0.23
    ãĥ¥ãĥ¼
    0.23
    æĸ°æĶ¿
    0.22
     забол
    0.22
    otine
    0.22
    arrants
    0.22
    ì°¬
    0.22
    è¡·
    0.21
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.