© 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. 24062
    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
    ountains
    -0.27
    imizer
    -0.27
    åĪ©çī©
    -0.25
    ħĮ
    -0.25
    abant
    -0.25
    istinguish
    -0.25
     Nam
    -0.24
    usz
    -0.24
    andest
    -0.24
    atab
    -0.23
    POSITIVE LOGITS
     beh
    0.29
    对èĩªå·±
    0.28
    :event
    0.26
    å¼ĵ
    0.26
    å¤ļå°ijéĴ±
    0.25
    è´¢
    0.25
    .Popup
    0.25
     MP
    0.24
    åIJ¸å¼ķ
    0.24
    éļIJ
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.