© 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. 87853
    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
    ost
    -0.27
    .ini
    -0.25
     suppose
    -0.25
    åıijçĶŁåľ¨
    -0.24
    doesn
    -0.24
    ãģ¤ãĤĤãĤĬ
    -0.24
     Princip
    -0.24
    åĩĭ
    -0.24
    riot
    -0.24
    å°±æĺ¯åĽłä¸º
    -0.24
    POSITIVE LOGITS
    igure
    0.27
     overd
    0.25
    åħŃ个
    0.25
    еÑĩно
    0.24
    erness
    0.24
    ä¿Ŀåģ¥
    0.23
    avers
    0.23
    MSG
    0.23
    awks
    0.23
    esson
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.