© 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. 30-TRANSCODER-HP
    7. 96822
    Prev
    Next
    INDEX
    Explanations

    online forms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ridden
    -0.27
    firebase
    -0.27
     fills
    -0.26
     program
    -0.26
    blocks
    -0.25
     programs
    -0.25
    fi
    -0.25
    æĶ¾è¿Ľ
    -0.25
    programs
    -0.25
     Twitch
    -0.25
    POSITIVE LOGITS
    >Contact
    0.27
    æݥ触
    0.26
    伸æīĭ
    0.26
    ovy
    0.26
    -Cs
    0.25
     trace
    0.25
    æĴ®
    0.25
    åĮ¹éħį
    0.25
    èĤļ
    0.25
    ismo
    0.24
    Activations Density 0.885%

    No Known Activations