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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 321
    Prev
    Next
    INDEX
    Explanations

    Network nodes and connections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oz
    -0.29
    `t
    -0.26
    elu
    -0.26
    é¢ĦæĬ¥
    -0.25
    antas
    -0.24
    phas
    -0.24
    èķ´åIJ«
    -0.24
     zza
    -0.24
     antis
    -0.24
     accesses
    -0.24
    POSITIVE LOGITS
     Accept
    0.27
    æİ¥åıĹäºĨ
    0.26
    Êĭ
    0.26
    ColumnName
    0.24
     baÅŁÄ±na
    0.24
     Pep
    0.24
    èIJ½
    0.24
    obile
    0.24
     Ãĸl
    0.24
    Accessory
    0.24
    Activations Density 1.983%

    No Known Activations