© 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. 161784
    Prev
    Next
    INDEX
    Explanations

    tasks

    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
    éĿ¢
    -0.28
    urious
    -0.26
    åĢĴ
    -0.26
    agnostic
    -0.26
    .springboot
    -0.25
    inati
    -0.25
    bject
    -0.25
    ilian
    -0.24
    å°¼
    -0.24
     ve
    -0.24
    POSITIVE LOGITS
     responsible
    0.31
    æķĪæŀľåĽ¾
    0.31
     responsibility
    0.29
    责任
    0.28
    (Func
    0.26
    ahi
    0.26
     Tup
    0.26
     responsável
    0.25
    èģĮè´£
    0.25
     fun
    0.25
    Activations Density 0.013%

    No Known Activations