© 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. 98505
    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
    uft
    -0.27
    åĿı
    -0.25
    ests
    -0.24
    _strerror
    -0.23
    æĹ¥æ¶Īæģ¯
    -0.23
     adel
    -0.23
     Disaster
    -0.23
    çģ¾éļ¾
    -0.23
    mit
    -0.23
     precisely
    -0.23
    POSITIVE LOGITS
    æķĪ
    0.28
    饱
    0.25
    uncated
    0.24
    ¦Ĥ
    0.24
    notated
    0.24
    ç¡Ģ
    0.24
     Hort
    0.24
    åİŁçIJĨ
    0.23
     efficacy
    0.23
    accessible
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.