© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111247
    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
    @update
    -0.30
    æľī没æľī
    -0.27
    engers
    -0.26
     Zap
    -0.25
    帼
    -0.25
    è¡ħ
    -0.24
    oline
    -0.24
    maid
    -0.24
    allenge
    -0.24
    å©¿
    -0.24
    POSITIVE LOGITS
    RICS
    0.25
    æīĢæıIJä¾Ľ
    0.25
     yourselves
    0.24
     Classes
    0.23
    rics
    0.23
     objeto
    0.23
    YOUR
    0.23
    Ư
    0.22
     Æ°u
    0.22
     Processes
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.