© 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. 32-TRANSCODER-HP
    7. 43893
    Prev
    Next
    INDEX
    Explanations

    French language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     optimal
    -0.38
     army
    -0.37
     essential
    -0.37
     alloy
    -0.36
     early
    -0.36
     injury
    -0.36
     assignment
    -0.36
     edge
    -0.36
     evil
    -0.35
     ugly
    -0.35
    POSITIVE LOGITS
    /an
    0.29
    ffects
    0.28
    ufs
    0.26
    ä¹±
    0.24
    æľīä¸Ģ天
    0.24
    çļĦéľĢæ±Ĥ
    0.23
    دÙī
    0.23
    åĪ©çĶ¨çİĩ
    0.23
     cid
    0.23
    lements
    0.23
    Activations Density 0.005%

    No Known Activations