© 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. 87665
    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
    ainer
    -0.29
    icc
    -0.27
     attackers
    -0.24
    INC
    -0.24
    yer
    -0.24
    itten
    -0.23
    NetMessage
    -0.23
    Öħ
    -0.23
    UNE
    -0.23
    æ¯ķä¸ļåIJİ
    -0.22
    POSITIVE LOGITS
     Tab
    0.27
    æķ´
    0.27
    çĽ²
    0.26
    çĻ¾
    0.25
    rench
    0.25
     Sacred
    0.25
     tab
    0.24
    é¢Ŀ
    0.24
    ÙĦد
    0.24
     Responsibility
    0.23
    Activations Density 0.070%

    No Known Activations

    This feature has no known activations.