© 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. 22-TRANSCODER-HP
    7. 87863
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    is
    -0.28
     ÑģпиÑģ
    -0.28
    æIJŀ好
    -0.27
    主管éĥ¨éŨ
    -0.27
    -0.27
    ÙĬØ©
    -0.26
    åĪ«è¯´
    -0.25
    å°±ç®Ĺ
    -0.25
    cape
    -0.24
    åĤĻ
    -0.24
    POSITIVE LOGITS
    ullo
    0.30
    ä¸įå¦Ĥ
    0.28
    atica
    0.28
    ä¸įå°ı
    0.27
    åľ¨äº¬
    0.26
    wdx
    0.26
    Tho
    0.26
    åĬŁåĬ³
    0.26
    WISE
    0.25
    以æĿ¥
    0.25
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.