© 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. 111280
    Prev
    Next
    INDEX
    Explanations

    or

    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
    两çĤ¹
    -0.29
    ñe
    -0.26
    è¶Ĭæĺ¯
    -0.26
    éŀħ
    -0.26
     ones
    -0.26
    è¿ľæĸ¹
    -0.25
    åħ³äºİæĪij们
    -0.25
     blur
    -0.25
    仲è£ģ
    -0.25
    ä»ĸ们ä¼ļ
    -0.24
    POSITIVE LOGITS
    DataTask
    0.30
    æĭ£
    0.29
    SORT
    0.24
    éĩĩ访æŶ
    0.24
    olest
    0.24
    念
    0.23
    oling
    0.23
    è¹²
    0.23
     Powell
    0.23
    orning
    0.23
    Activations Density 0.005%

    No Known Activations