© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24649
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éĢł
    -0.32
    æªĢ
    -0.29
    æŁ°
    -0.28
    ç§ijæķĻ
    -0.26
    çľĭ
    -0.26
    èĺĸ
    -0.24
    AMA
    -0.24
    _NR
    -0.24
    ]];↵↵
    -0.24
    Fri
    -0.23
    POSITIVE LOGITS
    osed
    0.28
    .tk
    0.27
    ä¸Ģéģį
    0.25
    è¿Ļ个游æĪı
    0.25
    á»įng
    0.25
    æŃ£æĸĩ
    0.24
     condos
    0.24
     Hutchinson
    0.24
     SIM
    0.24
    模仿
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.