© 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. 18-TRANSCODER-HP
    7. 89902
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ej
    -0.28
    yas
    -0.27
    war
    -0.27
    WAR
    -0.26
     converged
    -0.25
    çļĦä¾ĭåŃIJ
    -0.24
    TV
    -0.24
    éĽĢ
    -0.24
    }|
    -0.24
    forth
    -0.24
    POSITIVE LOGITS
     root
    0.28
    çīĪæĿĥ
    0.28
    æ´²
    0.25
    è®®äºĭ
    0.25
    å·¥ç¨ĭæĬĢæľ¯
    0.24
     russe
    0.24
     blockSize
    0.24
     scissors
    0.23
    èģĶ
    0.23
    åķ¬
    0.23
    Activations Density 0.143%

    No Known Activations

    This feature has no known activations.