© 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. 162741
    Prev
    Next
    INDEX
    Explanations

    out

    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
    è¯Ńæ°Ķ
    -0.30
    ensi
    -0.28
    perator
    -0.26
    éĢ¸
    -0.25
    æķ·
    -0.25
    =__
    -0.24
    pgsql
    -0.24
     egt
    -0.24
    kart
    -0.24
    never
    -0.24
    POSITIVE LOGITS
     spec
    0.27
     tend
    0.27
    ine
    0.26
    çļĦå·¥ä½ľ
    0.26
     number
    0.26
    инÑĦ
    0.25
    åĽº
    0.25
     quant
    0.24
    äºĨå¤ļå°ij
    0.24
     un
    0.24
    Activations Density 0.035%

    No Known Activations