© 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. 161614
    Prev
    Next
    INDEX
    Explanations

    Titles

    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
    ngine
    -0.28
    igu
    -0.26
    anges
    -0.25
    çľ¼åħī
    -0.25
    acted
    -0.25
    licated
    -0.24
    anged
    -0.24
     glob
    -0.24
     Philosoph
    -0.24
    ä¸ĸçķĮåIJĦåľ°
    -0.23
    POSITIVE LOGITS
    åģĥ
    0.27
    秣éĩij
    0.26
    ä¸įä¸ĭ
    0.26
    æı¡æīĭ
    0.25
    æ³
    0.25
    zee
    0.25
    æı¡ä½ı
    0.25
    为空
    0.25
    å²ģ以ä¸ĭ
    0.25
    front
    0.24
    Activations Density 0.005%

    No Known Activations