© 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. 64495
    Prev
    Next
    INDEX
    Explanations

    is

    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
     holland
    -0.28
    pections
    -0.28
     sacrificed
    -0.27
     shave
    -0.27
    ighth
    -0.27
    aven
    -0.26
     bureaucr
    -0.26
    Ãłn
    -0.26
     vern
    -0.25
    ereg
    -0.25
    POSITIVE LOGITS
     bi
    0.31
    éĢĹ
    0.28
    _same
    0.26
    åıªæľīä¸Ģ个
    0.26
    .ms
    0.26
    ä¹ł
    0.25
    	LP
    0.25
     same
    0.25
    æľī两个
    0.25
     Bi
    0.24
    Activations Density 26.092%

    No Known Activations