© 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. 131005
    Prev
    Next
    INDEX
    Explanations

    4

    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
    	anim
    -0.28
    ause
    -0.27
    agi
    -0.27
     --↵↵
    -0.26
    tg
    -0.26
    icl
    -0.25
    entr
    -0.25
     Clause
    -0.24
     ones
    -0.24
    assin
    -0.24
    POSITIVE LOGITS
     presence
    0.27
     séjour
    0.25
    æĩĤäºĭ
    0.25
    å¹Ķ
    0.24
    活泼
    0.24
    èµĸ以
    0.24
     présence
    0.24
    åij¨å²ģ
    0.24
    ç»ıéªĮåĴĮ
    0.23
     Presence
    0.23
    Activations Density 0.037%

    No Known Activations