© 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. 129868
    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
    heet
    -0.27
    è¯Ŀ
    -0.26
    åıĬ以ä¸Ĭ
    -0.26
    emics
    -0.24
    åĭ¢
    -0.24
     happened
    -0.23
    vore
    -0.23
    upt
    -0.23
    çįŃ
    -0.23
     wasting
    -0.22
    POSITIVE LOGITS
     finalist
    0.31
    quirer
    0.26
    riteln
    0.24
     Inquiry
    0.24
    quia
    0.24
    èī²å½©
    0.24
    ennessee
    0.24
    atalog
    0.23
    пÑĢоÑģ
    0.23
     evalu
    0.23
    Activations Density 0.035%

    No Known Activations

    This feature has no known activations.