© 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. 142618
    Prev
    Next
    INDEX
    Explanations

    Removing or stopping something

    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
    Negative Logits
    asco
    -0.27
    ereo
    -0.27
    icher
    -0.25
    éĩįè§Ĩ
    -0.25
    exion
    -0.25
     Neutral
    -0.25
    edian
    -0.24
     avoid
    -0.24
    disp
    -0.24
    icina
    -0.23
    POSITIVE LOGITS
    yle
    0.31
    ãi
    0.27
     expressing
    0.26
    ye
    0.26
     overd
    0.25
    ointed
    0.24
    æ¼ī
    0.24
    ä¸ĬåѦ
    0.24
    express
    0.24
    禽
    0.24
    Activations Density 29.051%

    No Known Activations