© 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. 87522
    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
     Sno
    -0.26
    rosse
    -0.26
    å»Ĭ
    -0.25
    说ä»Ģä¹Ī
    -0.25
    ennes
    -0.24
    .sponge
    -0.24
    allee
    -0.24
    udit
    -0.24
    å¾ĩ
    -0.24
     soup
    -0.23
    POSITIVE LOGITS
    berry
    0.28
    æĹ¶è¾°
    0.26
     '~
    0.25
     Sy
    0.25
    Features
    0.25
    ä¸įåħ·å¤ĩ
    0.24
     EV
    0.24
    fair
    0.24
    éĴĵé±¼
    0.24
    .plist
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.