© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29127
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    顺
    -0.30
    éĩįçĤ¹
    -0.30
    tek
    -0.27
     initState
    -0.25
    },${
    -0.25
    æķħå±ħ
    -0.24
    æľīæĿ¡ä»¶çļĦ
    -0.24
    üp
    -0.24
     divorced
    -0.24
     divor
    -0.24
    POSITIVE LOGITS
    yre
    0.29
    为ä¼ģä¸ļ
    0.28
    åĿŀ
    0.27
    车åĨħ
    0.27
    amiliar
    0.26
    unch
    0.26
    niest
    0.26
    ENCH
    0.26
     Faces
    0.25
    arth
    0.25
    Activations Density 2.514%

    No Known Activations