© 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. 24-TRANSCODER-HP
    7. 151440
    Prev
    Next
    INDEX
    Explanations

    scientific publication references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     kern
    -0.28
    .hardware
    -0.26
     Ten
    -0.26
    tracts
    -0.26
     scenario
    -0.25
    illac
    -0.25
    .Standard
    -0.24
     press
    -0.24
    fall
    -0.24
    鸵
    -0.24
    POSITIVE LOGITS
    aurus
    0.31
    `\
    0.26
    åı·
    0.25
    楣
    0.25
    XR
    0.25
    åĪ¶
    0.24
    WL
    0.24
    sı
    0.24
    çıī
    0.24
    é¢ĦåijĬ
    0.24
    Activations Density 0.502%

    No Known Activations