© 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. 130160
    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
    çŃĶåºĶ
    -0.29
    xca
    -0.28
    èī²
    -0.26
     Props
    -0.24
     contacts
    -0.24
    agle
    -0.24
    specific
    -0.24
    contracts
    -0.24
     verm
    -0.24
     phen
    -0.24
    POSITIVE LOGITS
    åħ¨éĿ¢
    0.27
    gun
    0.25
    indsay
    0.25
    pole
    0.25
     med
    0.24
    é²Ī
    0.24
     further
    0.24
     ours
    0.24
    orney
    0.23
    ew
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.