© 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. 161856
    Prev
    Next
    INDEX
    Explanations

    w

    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
    è¦ģ好好
    -0.31
    ä½İ声
    -0.28
    auge
    -0.24
    èĽ®
    -0.24
    è¿ĻäºĽéĹ®é¢ĺ
    -0.23
    elect
    -0.23
    御
    -0.23
    SHARE
    -0.23
    è¿IJæ°Ķ
    -0.23
    PHA
    -0.23
    POSITIVE LOGITS
     resulting
    0.28
     ensuing
    0.27
    ibly
    0.26
    å¨ĺ
    0.26
    les
    0.25
    åĵ¨
    0.24
     Ars
    0.24
    hir
    0.24
    æĭĽ
    0.24
    opsy
    0.23
    Activations Density 0.018%

    No Known Activations