© 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. 151288
    Prev
    Next
    INDEX
    Explanations

    Abstracted text excerpts

    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
    è°ª
    -0.27
    鸾
    -0.27
    borg
    -0.26
    è¡¥
    -0.25
     fulfil
    -0.25
    dy
    -0.25
     tractor
    -0.24
    eid
    -0.24
    æľºåĻ¨
    -0.24
    欣
    -0.24
    POSITIVE LOGITS
    sharing
    0.26
    endregion
    0.26
    itore
    0.25
    rones
    0.25
    Void
    0.25
    nothing
    0.24
     sharing
    0.24
    shares
    0.24
     cluster
    0.24
     rebounds
    0.24
    Activations Density 0.080%

    No Known Activations