© 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. 33-TRANSCODER-HP
    7. 52590
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    anes
    -0.33
    åĨķ
    -0.27
    è¯Ľ
    -0.25
    lices
    -0.25
    олод
    -0.25
     hang
    -0.25
    uvw
    -0.24
    åıij
    -0.24
     ali
    -0.24
    æŀķ头
    -0.24
    POSITIVE LOGITS
     Answers
    0.27
    owns
    0.26
     si
    0.26
    iare
    0.25
    ereco
    0.25
    ucas
    0.24
    SO
    0.24
    åijĬè¯īä»ĸ
    0.24
    (CharSequence
    0.23
    å¤īãģĪ
    0.23
    Activations Density 0.087%

    No Known Activations