© 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. 161742
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    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
    ä»ĭ
    -0.28
    忽
    -0.26
    æĭ¿åĩº
    -0.26
     underst
    -0.25
     foreground
    -0.25
    imators
    -0.24
     Gle
    -0.24
     declaration
    -0.24
    æĶ¾æīĭ
    -0.23
    моÑĤ
    -0.23
    POSITIVE LOGITS
     count
    0.70
    count
    0.63
    计
    0.63
    Counter
    0.62
    Count
    0.60
     Count
    0.60
    COUNT
    0.59
     counter
    0.58
    _count
    0.58
    counter
    0.58
    Activations Density 0.020%

    No Known Activations