© 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. 97345
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    çĶ±äºİ
    -0.55
    çĶ±æĸ¼
    -0.40
    åĽłä¸º
    -0.36
    åĽł
    -0.36
     due
    -0.36
    due
    -0.35
    åĽłåħ¶
    -0.35
     wegen
    -0.33
     Due
    -0.33
    Due
    -0.33
    POSITIVE LOGITS
     tin
    0.27
    occup
    0.25
     traced
    0.24
    _NEED
    0.24
     streak
    0.24
     beloved
    0.23
    velopment
    0.23
    éĴĩ
    0.23
    忧
    0.23
    irth
    0.22
    Activations Density 0.001%

    No Known Activations