© 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. 150326
    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
     tune
    -0.28
    /popper
    -0.28
    -fill
    -0.24
    -validate
    -0.23
    lsx
    -0.23
    æĻ®éĢļè¯Ŀ
    -0.23
    arged
    -0.23
    uien
    -0.23
    esser
    -0.23
    鹫
    -0.23
    POSITIVE LOGITS
    ",__
    0.28
    ncoder
    0.28
    轨
    0.26
     intr
    0.26
     argc
    0.25
    è¦ģä¹Ī
    0.25
    è§Ĵ
    0.24
    ä¸ļåĨħ
    0.24
    agn
    0.23
    endregion
    0.23
    Activations Density 0.157%

    No Known Activations

    This feature has no known activations.