© 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. 23-TRANSCODER-HP
    7. 161700
    Prev
    Next
    INDEX
    Explanations

    Incomplete sentences and code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç´«èī²
    -0.31
     Prec
    -0.28
    ulates
    -0.27
     distributions
    -0.26
     plus
    -0.26
     plum
    -0.25
     distribution
    -0.25
     Nak
    -0.25
    à¸Ķาร
    -0.24
     solid
    -0.24
    POSITIVE LOGITS
    ImageContext
    0.27
    stones
    0.27
    apolis
    0.27
    castle
    0.27
    -eff
    0.26
    REW
    0.25
    wards
    0.25
    ennes
    0.25
    parison
    0.24
    æĻļä¼ļ
    0.24
    Activations Density 0.004%

    No Known Activations