© 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. 24-TRANSCODER-HP
    7. 150674
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    bris
    -0.25
    _POINTER
    -0.25
    çĺ¢
    -0.25
     aisle
    -0.25
     Repos
    -0.24
    èĩ¾
    -0.24
    onDelete
    -0.24
     dilig
    -0.24
    born
    -0.24
    IRA
    -0.24
    POSITIVE LOGITS
    æĹłè®ºå¦Ĥä½ķ
    0.32
    UIS
    0.25
    诸èijĽäº®
    0.25
    ifest
    0.24
    zo
    0.24
    æŀģ
    0.24
    ature
    0.23
    -Cs
    0.23
     feasibility
    0.23
    æīİ
    0.23
    Activations Density 0.066%

    No Known Activations

    This feature has no known activations.