© 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. 111782
    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
    ounc
    -0.29
    æ¹ĸåĮº
    -0.26
    unately
    -0.26
    ickers
    -0.25
    å½ĵãģŁãĤĬ
    -0.25
    _ptr
    -0.24
    ovsky
    -0.24
    ewitness
    -0.24
     literally
    -0.24
    irms
    -0.24
    POSITIVE LOGITS
    ³³
    0.26
    robat
    0.25
    iri
    0.23
    ijkl
    0.23
    æĽ´
    0.23
     resolution
    0.23
    ocoder
    0.23
     adjunct
    0.23
     sui
    0.23
    atories
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.