© 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. 20-TRANSCODER-HP
    7. 140899
    Prev
    Next
    INDEX
    Explanations

    sufficient

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įä»ħæĺ¯
    -0.29
     Concepts
    -0.25
     _:
    -0.25
    AWN
    -0.25
     dialogRef
    -0.24
    (ref
    -0.24
    [label
    -0.24
    çļĦ身份
    -0.24
    hift
    -0.24
    ahl
    -0.24
    POSITIVE LOGITS
     fall
    0.28
     simply
    0.28
     cleaning
    0.27
     desert
    0.27
     sense
    0.27
     revers
    0.26
     falls
    0.26
    ichert
    0.26
     trail
    0.25
    /python
    0.25
    Activations Density 13.980%

    No Known Activations