© 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. 130714
    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
    ENG
    -0.26
    ziej
    -0.26
    PAL
    -0.26
    abouts
    -0.24
    .PUT
    -0.24
    å±ŀäºİ
    -0.23
    metric
    -0.23
    éĢĶä¸Ń
    -0.23
    .Invariant
    -0.23
     bout
    -0.23
    POSITIVE LOGITS
    çłľ
    0.29
    åĪ»æĦı
    0.28
    )...
    0.26
     bli
    0.25
     intentionally
    0.25
     Dy
    0.24
    [tag
    0.24
    iesz
    0.24
    RELEASE
    0.24
    ottage
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.