© 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. 18-TRANSCODER-HP
    7. 88382
    Prev
    Next
    INDEX
    Explanations

    GPS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    igation
    -0.30
    æļĤæŶ
    -0.28
     temporary
    -0.26
    growth
    -0.26
    åĩŃ
    -0.26
    åıijçĶŁåľ¨
    -0.25
    ordered
    -0.25
     temporal
    -0.25
    pod
    -0.25
    æīĵçł´äºĨ
    -0.25
    POSITIVE LOGITS
    adera
    0.31
    /rem
    0.27
    nie
    0.26
    .Conn
    0.25
     Becker
    0.25
     tipping
    0.25
    å½ĵçĦ¶æĺ¯
    0.25
     ÑĢÑıдом
    0.24
     BED
    0.24
    LEY
    0.24
    Activations Density 7.896%

    No Known Activations