© 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. 97329
    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
     graded
    -0.26
    ted
    -0.25
    dden
    -0.25
     side
    -0.25
     herself
    -0.24
     fact
    -0.24
     automatic
    -0.24
    åħ±å»º
    -0.24
    çĵ¦
    -0.24
     Dao
    -0.24
    POSITIVE LOGITS
    TRIES
    0.28
    PLUS
    0.27
    è´§çī©
    0.25
     nét
    0.24
    otor
    0.24
     изделиÑı
    0.24
    ystick
    0.24
    elog
    0.23
     kê
    0.23
    modification
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.