© 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. 35-TRANSCODER-HP
    7. 40317
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     )↵↵↵↵↵↵↵↵
    -0.27
    çī¹æ®Ĭ
    -0.26
    ç»Ħ
    -0.25
     \`
    -0.24
    imeo
    -0.24
    çī¹ç§į
    -0.24
    usal
    -0.23
     inf
    -0.23
    xBD
    -0.23
    çµĦ
    -0.23
    POSITIVE LOGITS
    æľīè¿Ļæł·çļĦ
    0.26
    è¿Ļç§įæĸ¹å¼ı
    0.26
    enza
    0.26
    å°±æĺ¯è¿Ļæł·
    0.25
     getter
    0.25
     hers
    0.25
    .intValue
    0.25
    éķij
    0.25
     Lena
    0.24
     jap
    0.24
    Activations Density 42.364%

    No Known Activations

    This feature has no known activations.