© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23599
    Prev
    Next
    INDEX
    Explanations

    Repetition, recurrence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    @section
    -0.25
    hooks
    -0.24
     convex
    -0.24
    illis
    -0.23
     originally
    -0.23
    uce
    -0.23
    iping
    -0.23
    èµŁ
    -0.23
    gger
    -0.23
     enim
    -0.23
    POSITIVE LOGITS
     again
    1.74
     Again
    1.54
    again
    1.53
    Again
    1.48
    åĨį次
    1.46
    åĨįä¸Ģ次
    1.23
    åıĪä¸Ģ次
    1.23
     wieder
    1.16
     novamente
    1.12
    åĨį度
    1.11
    Activations Density 0.026%

    No Known Activations