© 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. 150923
    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
     dest
    -0.27
    åĮºåĪ«
    -0.26
    ุ
    -0.26
    eking
    -0.25
    æĸ«
    -0.25
    稳妥
    -0.24
    ób
    -0.24
     Interr
    -0.24
    @class
    -0.24
    ativity
    -0.23
    POSITIVE LOGITS
    egra
    0.25
    .linkedin
    0.23
     BAB
    0.23
    wers
    0.23
     setVisible
    0.23
    åĽĬ
    0.23
    é»İæĺİ
    0.23
     Yours
    0.23
    é¦Ī
    0.23
     devise
    0.22
    Activations Density 0.887%

    No Known Activations

    This feature has no known activations.