© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88920
    Prev
    Next
    INDEX
    Explanations

    Random information snippets

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ross
    -0.26
    èĢĮä¸įæĺ¯
    -0.26
    èĢĮéĿŀ
    -0.26
    èĤĺ
    -0.25
     createStackNavigator
    -0.25
    主æµģ
    -0.25
    static
    -0.24
    ìŀĦ
    -0.24
    ippy
    -0.24
    sm
    -0.24
    POSITIVE LOGITS
     hitch
    0.27
    brtc
    0.24
    ificate
    0.24
     Sahara
    0.24
     fours
    0.23
    HEME
    0.23
    æĪIJè´¥
    0.23
    ä¸ĩæĪ·
    0.23
     adopts
    0.23
    ç¡ķ士
    0.23
    Activations Density 3.106%

    No Known Activations