© 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. 41143
    Prev
    Next
    INDEX
    Explanations

    Religious topics

    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
     Cellular
    -0.27
    igm
    -0.27
    ÑĤа
    -0.26
     gin
    -0.25
     Mono
    -0.25
    HA
    -0.24
    é«ĺ
    -0.24
     imp
    -0.24
    QA
    -0.24
     cellular
    -0.24
    POSITIVE LOGITS
     па
    0.28
    kek
    0.27
     ÐŁÐ°ÑĢ
    0.27
    ket
    0.26
     rect
    0.26
    ene
    0.25
     par
    0.25
     ECC
    0.25
    паÑĢ
    0.25
    å°±çŁ¥éģĵ
    0.25
    Activations Density 0.006%

    No Known Activations