© 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. 24477
    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
     unknow
    -0.29
    emann
    -0.28
    ä»ĺ
    -0.26
    iamond
    -0.26
    æĸĩåĮĸåĴĮ
    -0.25
    å°ıåºĹ
    -0.24
    pcm
    -0.24
    ored
    -0.24
    大æłij
    -0.24
    åĮºåĨħ
    -0.24
    POSITIVE LOGITS
    ARIO
    0.31
     return
    0.26
    ieu
    0.25
    rine
    0.25
     extent
    0.25
    hone
    0.25
    ahn
    0.24
    ndern
    0.24
     option
    0.24
    hor
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.