© 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. 150323
    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
    cil
    -0.28
    uada
    -0.27
    åĴ¥
    -0.27
    èIJ¼
    -0.26
    åIJ¬çĿĢ
    -0.24
    åķĨçĶ¨
    -0.24
    mercial
    -0.24
    åIJ¬å¾Ĺ
    -0.24
    éĹ»è¨Ģ
    -0.24
    æģ¯
    -0.24
    POSITIVE LOGITS
    *č↵
    0.30
     descon
    0.27
    untime
    0.27
    !č↵
    0.26
    ogn
    0.26
    aria
    0.25
    č↵
    0.25
    ä¸ªé¡¹çĽ®
    0.25
    åĩłæ¬¡
    0.24
    -scale
    0.24
    Activations Density 0.921%

    No Known Activations

    This feature has no known activations.