© 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. 98421
    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
    çļĦèĥĮåIJİ
    -0.30
    elight
    -0.29
    ugin
    -0.27
    马åĬĽ
    -0.26
     Foot
    -0.26
     ..."↵↵
    -0.26
     Cha
    -0.26
     indiv
    -0.25
     Sco
    -0.25
    antino
    -0.24
    POSITIVE LOGITS
    åĵ¼
    0.26
    éľī
    0.25
    idd
    0.25
     annoying
    0.25
    illo
    0.25
    æŃĮ
    0.24
    Verse
    0.24
    AnimationFrame
    0.24
    ez
    0.24
    Mer
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.