© 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. 87117
    Prev
    Next
    INDEX
    Explanations

    punctuation and "and"

    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
    les
    -0.28
    å¤ļä¹ħ
    -0.25
     Majesty
    -0.25
    oss
    -0.25
    Īëĭ¤
    -0.24
    issy
    -0.24
    æĸĭ
    -0.24
    formats
    -0.24
    Dispose
    -0.23
    ä¸Ģ天
    -0.23
    POSITIVE LOGITS
    æŃ¤æ¬¡æ´»åĬ¨
    0.29
    mutable
    0.28
     stacked
    0.28
    mue
    0.26
    TRL
    0.25
    æŃ£åľ¨è¿Ľè¡Į
    0.25
    è¿«ä¸įåıĬå¾ħ
    0.25
     Tutor
    0.24
    initial
    0.24
     Initial
    0.24
    Activations Density 0.010%

    No Known Activations