© 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. 140885
    Prev
    Next
    INDEX
    Explanations

    animals

    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
    wan
    -0.27
    éĽĨä½ĵ
    -0.27
    (Screen
    -0.26
    ãĥŁ
    -0.26
    è°ģ
    -0.24
    soup
    -0.24
    å±Ģéķ¿
    -0.24
    PHONE
    -0.24
     Soup
    -0.24
    ÃŃm
    -0.23
    POSITIVE LOGITS
    çļĦåIJĦ项
    0.27
    åĴĮåıijå±ķ
    0.26
     moment
    0.25
     polar
    0.24
     moments
    0.24
     di
    0.23
     present
    0.23
    åĴĮæĶ¯æĮģ
    0.23
     Innovative
    0.23
    åĨħ饰
    0.23
    Activations Density 9.887%

    No Known Activations