© 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. 130432
    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
    cular
    -0.30
     Dial
    -0.27
    âľĶ
    -0.25
    avoid
    -0.25
     stressed
    -0.25
    ries
    -0.25
    é¦Ļæ°´
    -0.24
    è¾Ļ
    -0.24
    æĿ¥è¯´
    -0.24
    ä¸ĩæĪ·
    -0.24
    POSITIVE LOGITS
    PING
    0.25
    æĢİ
    0.24
     Mét
    0.24
    èį£èªī
    0.24
    allis
    0.23
    atu
    0.23
    LINK
    0.23
    绵
    0.22
    æķĪçĽĬ
    0.22
    cairo
    0.22
    Activations Density 0.030%

    No Known Activations

    This feature has no known activations.