© 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. 54514
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    äºļ
    -0.30
    顺
    -0.28
     marg
    -0.28
    æķijçģ¾
    -0.28
    äºŀ
    -0.27
    梨
    -0.27
    æ¶Īéĺ²
    -0.26
    ấn
    -0.26
    伤
    -0.25
    æijĨ
    -0.25
    POSITIVE LOGITS
     compound
    0.34
     simplex
    0.29
     Compound
    0.28
    èģĺ请
    0.27
    Compound
    0.27
    compound
    0.27
     ó
    0.27
     compounds
    0.27
    åĮĸåIJĪçī©
    0.27
     mind
    0.26
    Activations Density 0.009%

    No Known Activations