© 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. 87376
    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
    éķĩæ±Ł
    -0.24
     disap
    -0.23
     Princip
    -0.23
    åºķå±Ĥ
    -0.23
     inde
    -0.23
    ALLY
    -0.23
     principals
    -0.23
    ç§įç§į
    -0.23
    HY
    -0.23
    undi
    -0.22
    POSITIVE LOGITS
    oux
    0.27
     implicitly
    0.25
    omin
    0.24
    implicitly
    0.24
    æµĴ
    0.23
    istica
    0.23
    éĩľ
    0.23
    acht
    0.23
     HOL
    0.22
    ä½İ头
    0.22
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.