© 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. 111078
    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
    Negative Logits
    @qq
    -0.31
    ioned
    -0.29
    è½»
    -0.26
    igne
    -0.26
    .retry
    -0.25
    inue
    -0.24
    é»Ħéĩij
    -0.24
    loads
    -0.24
    upp
    -0.24
    (Layout
    -0.23
    POSITIVE LOGITS
     resc
    0.27
     tors
    0.26
     po
    0.26
     fill
    0.26
     previous
    0.25
    ä¸ĸéĹ´
    0.25
    åħ·ä½ĵæĥħåĨµ
    0.25
     Situation
    0.25
     Fill
    0.25
     Sor
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.