© 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. 142503
    Prev
    Next
    INDEX
    Explanations

    J

    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
     ?↵
    -0.32
     dro
    -0.26
    oo
    -0.26
    dro
    -0.26
     recovered
    -0.25
     ?
    -0.25
    _↵
    -0.25
    erv
    -0.25
    errat
    -0.24
     riv
    -0.24
    POSITIVE LOGITS
    odox
    0.32
    ece
    0.28
    å¼Ħå¾Ĺ
    0.26
    åį°åº¦
    0.26
    екÑĤ
    0.26
    antity
    0.25
    åĩĢ
    0.25
    èļ±
    0.23
    æ¾Ħæ¸ħ
    0.23
    afb
    0.23
    Activations Density 1.390%

    No Known Activations