© 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. 87914
    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
    .setter
    -0.28
    plr
    -0.27
    (padding
    -0.27
    .ma
    -0.26
    WithIdentifier
    -0.25
     buses
    -0.25
    ä½ĨæĪij们
    -0.25
    .Sin
    -0.25
    inee
    -0.24
    bout
    -0.24
    POSITIVE LOGITS
    æĭĻ
    0.27
    æĮij
    0.26
    å¼Ĥ
    0.26
    æĸ°é²ľ
    0.26
    rp
    0.25
    åĨ²
    0.25
    临æŶ
    0.24
     magazine
    0.24
    çĵ¶
    0.24
    [j
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.