© 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. 22-TRANSCODER-HP
    7. 88626
    Prev
    Next
    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugs
    -0.27
    cape
    -0.27
    scape
    -0.27
    åİĨåı²æĸ°
    -0.26
    缮åīį为æŃ¢
    -0.25
    管çIJĨæĿ¡ä¾ĭ
    -0.25
    sil
    -0.25
    kÄħ
    -0.25
     branches
    -0.24
    bara
    -0.24
    POSITIVE LOGITS
     Ele
    0.29
     ele
    0.28
    orch
    0.27
     ìĪĺëıĦ
    0.27
    .ar
    0.25
     Sept
    0.24
    é²ľ
    0.24
    Opt
    0.24
    审
    0.24
    ENSE
    0.24
    Activations Density 0.007%

    No Known Activations