© 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. 161910
    Prev
    Next
    INDEX
    Explanations

    init

    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
    OperationException
    -0.27
    æ»ķ
    -0.26
    things
    -0.26
    annels
    -0.26
     *&
    -0.24
    itud
    -0.24
    mar
    -0.23
    主èIJ¥ä¸ļ
    -0.23
    kü
    -0.23
    رÙĩ
    -0.23
    POSITIVE LOGITS
    alli
    0.31
    ochond
    0.27
    chy
    0.26
    ches
    0.26
    æĭ®
    0.24
    chema
    0.24
    rophy
    0.23
    rophic
    0.23
    åħ±çĶŁ
    0.23
    oulos
    0.23
    Activations Density 0.040%

    No Known Activations