© 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. 24-TRANSCODER-HP
    7. 151243
    Prev
    Next
    INDEX
    Explanations

    Math and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åIJij社ä¼ļ
    -0.29
    è®°
    -0.28
    ä¸ĵèģĮ
    -0.27
    ä»İ严
    -0.25
    			 ↵
    -0.25
    abant
    -0.25
     pumped
    -0.25
    å¾Īå°ı
    -0.24
    arshal
    -0.24
    éĺ³
    -0.24
    POSITIVE LOGITS
    Enumerator
    0.32
    eft
    0.27
    èĢģå®ŀ
    0.26
     depart
    0.25
    å¢ĥ
    0.25
    _receipt
    0.25
     survival
    0.25
    æĹģ
    0.25
     дов
    0.24
    led
    0.24
    Activations Density 0.900%

    No Known Activations