© 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. 270
    Prev
    Next
    INDEX
    Explanations

    cooperative

    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
    丰
    -0.30
    èIJ½
    -0.27
    åı¦ä¸Ģä½į
    -0.26
    硬
    -0.25
     abund
    -0.25
    èĶļ
    -0.24
    éĢĢå½¹
    -0.24
     Silent
    -0.24
    æµĵ
    -0.24
     errMsg
    -0.24
    POSITIVE LOGITS
    aload
    0.27
    ören
    0.26
    缼å¼Ģ
    0.26
    osaur
    0.26
    acional
    0.25
    ceptor
    0.25
     Flood
    0.25
    æIJĶ
    0.24
    ÑĦи
    0.24
     Lö
    0.24
    Activations Density 0.011%

    No Known Activations