© 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. 145
    Prev
    Next
    INDEX
    Explanations

    h

    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
    æīİ
    -0.25
    æ±ł
    -0.24
    æĽ´å¤ļ
    -0.24
    åIJĮæł·
    -0.24
    磶
    -0.24
     ëıĮ
    -0.23
    atorio
    -0.23
    å®ļåĪ¶
    -0.23
    omics
    -0.23
     boards
    -0.23
    POSITIVE LOGITS
    åĻ¨å®ĺ
    0.26
    ahead
    0.25
    adget
    0.25
    åīįéĢĶ
    0.25
    arat
    0.24
     Ahead
    0.24
    eec
    0.24
    è³ŀ
    0.24
    PROTO
    0.24
    /target
    0.24
    Activations Density 0.043%

    No Known Activations