© 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. 98472
    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
    çĽijçĿ£
    -0.21
    éķĤ
    -0.21
    haul
    -0.21
    ignite
    -0.20
    heat
    -0.20
     haci
    -0.20
     |/
    -0.20
     WARN
    -0.20
    æĬ¥å¤į
    -0.20
    va
    -0.20
    POSITIVE LOGITS
    arro
    0.24
    oins
    0.23
    irror
    0.23
    iet
    0.23
    InputStream
    0.23
     freshly
    0.22
    valu
    0.22
    imat
    0.21
     arrivals
    0.21
    çijĢ
    0.21
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.