© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25481
    Prev
    Next
    INDEX
    Explanations

    completion

    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
    Negative Logits
    è¿ĩåİ»äºĨ
    -0.29
     past
    -0.29
    anmar
    -0.28
    åĭĸ
    -0.27
     noreferrer
    -0.26
    ousse
    -0.25
     Cong
    -0.25
    åıijå±ķæł¼å±Ģ
    -0.25
    ounced
    -0.24
    structor
    -0.24
    POSITIVE LOGITS
    æŃ»äº¡
    0.27
    æĸ¹
    0.26
    __/
    0.25
    èĢį
    0.25
    éĺ´éĺ³
    0.24
    ä»Ĭ天çļĦ
    0.24
     вним
    0.24
    ä¼ļéķ¿
    0.24
    pie
    0.23
    å¹³åı°
    0.23
    Activations Density 0.036%

    No Known Activations