© 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. 131045
    Prev
    Next
    INDEX
    Explanations

    academic/scientific text

    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
    Ã¼ÃŁ
    -0.28
    ï¼īč↵
    -0.26
    éĻ¢éĻ¢å£«
    -0.25
    ][/
    -0.25
    Tur
    -0.25
    (Keys
    -0.24
    èį£èªī称åı·
    -0.24
     Tur
    -0.24
    uft
    -0.23
    Ĥ¨
    -0.23
    POSITIVE LOGITS
    æĭį
    0.26
    æĥķ
    0.25
    tsx
    0.25
    бл
    0.25
     Directed
    0.24
    akedown
    0.24
    åįıè°ĥ
    0.24
     secret
    0.24
    åĨħå¤ĸ
    0.24
    bob
    0.23
    Activations Density 7.486%

    No Known Activations