© 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. 88789
    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
    ieu
    -0.25
    ikel
    -0.25
    ’T
    -0.24
    annels
    -0.24
    asa
    -0.24
    aza
    -0.24
    ä¸Ģèĩ´æĢ§
    -0.23
    åĬ¨ä½ľ
    -0.23
    ActionResult
    -0.23
    ’t
    -0.23
    POSITIVE LOGITS
    ç©¿è¿ĩ
    0.28
     snaps
    0.25
    æ¹¾åĮº
    0.24
    rios
    0.23
    综åIJĪ
    0.23
    éĶIJ
    0.23
     wrink
    0.23
    综åIJĪæ²»çIJĨ
    0.23
     decimals
    0.23
    åīį沿
    0.23
    Activations Density 56.733%

    No Known Activations

    This feature has no known activations.