© 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. 87988
    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
     margins
    -0.28
    çİ©ç¬ij
    -0.28
    jar
    -0.27
    èĩªåįij
    -0.27
     Grip
    -0.26
     publishing
    -0.25
     GetMessage
    -0.24
    èįĨ
    -0.23
    ä¿¡æģ¯æľįåĬ¡
    -0.23
    strt
    -0.23
    POSITIVE LOGITS
    ç½®
    0.26
    mall
    0.25
    éŃĦ
    0.25
     adm
    0.24
    adium
    0.24
     ple
    0.24
     fandom
    0.24
     underst
    0.23
    ogram
    0.23
    rale
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.