© 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. 19-TRANSCODER-HP
    7. 7824
    Prev
    Next
    INDEX
    Explanations

    repeating a process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vest
    -0.27
     Fork
    -0.26
     confess
    -0.26
    èIJ½åħ¥
    -0.25
    ç½ij约
    -0.25
    纪念
    -0.24
    _FALL
    -0.24
    enaries
    -0.24
    ettle
    -0.24
     confessed
    -0.23
    POSITIVE LOGITS
     repeated
    0.59
     repeat
    0.53
    éĩįå¤į
    0.50
    repeat
    0.49
     repeatedly
    0.46
     repeating
    0.45
    -repeat
    0.44
    åıįå¤į
    0.44
    .repeat
    0.44
     repeats
    0.43
    Activations Density 0.017%

    No Known Activations