© 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. 111995
    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
     phys
    -0.27
    è°
    -0.26
     dem
    -0.26
     nons
    -0.25
     elev
    -0.24
     mod
    -0.24
    è¯
    -0.24
    .getBy
    -0.24
    PHA
    -0.24
    semb
    -0.23
    POSITIVE LOGITS
     Booker
    0.27
    âĢ¦↵↵↵
    0.26
    æĪĺ士
    0.25
    zÅij
    0.25
    æ®ĺ
    0.25
    ün
    0.25
    åī¯ä¹¦è®°
    0.24
    liner
    0.24
    roe
    0.23
    å®ĺåijĺ
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.