© 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. 97726
    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
    ibile
    -0.28
    館
    -0.26
    å¯Ŀ
    -0.25
     sockets
    -0.25
     continued
    -0.24
    åĩ¡æĺ¯
    -0.24
    éĺŁåijĺ
    -0.24
    -player
    -0.24
    ç¶
    -0.23
    åľ°ä¸ĭ
    -0.23
    POSITIVE LOGITS
    人家
    0.29
    gars
    0.26
    steen
    0.25
    antium
    0.25
    quiv
    0.24
    ycin
    0.24
    æĢµ
    0.24
    éħ¬
    0.24
    arms
    0.23
     protector
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.