© 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. 110961
    Prev
    Next
    INDEX
    Explanations

    Code and scripting

    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
    Negative Logits
    mounted
    -0.35
     mounted
    -0.28
    throat
    -0.27
     mounts
    -0.26
    çľĭæĿ¥
    -0.26
    çĻ»
    -0.26
    .responseText
    -0.25
    è¾ķ
    -0.25
     relation
    -0.24
    è·£
    -0.24
    POSITIVE LOGITS
    è³ĩ
    0.28
     знак
    0.26
     %+
    0.26
    ìĽĢ
    0.25
    eyond
    0.25
    æ·±
    0.24
     precious
    0.24
     Treasure
    0.24
    æĿ¥çĶµ
    0.24
    ohana
    0.24
    Activations Density 0.001%

    No Known Activations