© 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. 97944
    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
    åķĦ
    -0.26
    atan
    -0.25
    rad
    -0.25
    åĨįä¸Ģ次
    -0.25
    grow
    -0.24
     precisely
    -0.24
    ί
    -0.23
    cas
    -0.23
     outsiders
    -0.23
    onis
    -0.23
    POSITIVE LOGITS
    )Math
    0.25
    çĶ³æĬ¥
    0.23
    çĶ³
    0.23
    leared
    0.23
    åı¯è¾¾
    0.23
    åı«å£°
    0.23
    -------------</
    0.22
    eller
    0.22
    æĬ¥
    0.22
    habi
    0.22
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.