© 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. 163077
    Prev
    Next
    INDEX
    Explanations

    measuring physical parameters

    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
     Sheets
    -0.29
    _AA
    -0.27
    runs
    -0.26
     ÑĥнивеÑĢÑģ
    -0.25
    ä¸Ģåı°
    -0.25
    åı¶
    -0.25
    ãĥ¼ãĤ¸
    -0.25
    Mirror
    -0.24
    éķľ
    -0.24
    约å®ļ
    -0.23
    POSITIVE LOGITS
     remot
    0.29
    è¡Ģåİĭ
    0.28
    亮度
    0.28
    assy
    0.27
     sweat
    0.26
    æĸ¹ä½į
    0.26
    že
    0.26
    çĥŃéĩı
    0.25
    åĵģä½į
    0.25
     arousal
    0.25
    Activations Density 0.004%

    No Known Activations