© 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. 43858
    Prev
    Next
    INDEX
    Explanations

    URLs and web data

    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
    Circular
    -0.29
    ption
    -0.25
     Circular
    -0.25
    ì¼ĵ
    -0.25
    Threads
    -0.24
     circular
    -0.24
    èİĵ
    -0.24
    andon
    -0.24
    еÑĩение
    -0.24
    idy
    -0.23
    POSITIVE LOGITS
     v
    0.40
     syn
    0.39
    Syn
    0.38
     V
    0.36
     Syn
    0.36
    é»Ħ
    0.34
    syn
    0.33
    V
    0.31
    v
    0.30
     Hood
    0.30
    Activations Density 0.007%

    No Known Activations