© 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. 54444
    Prev
    Next
    INDEX
    Explanations

    academic/technical texts

    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
    æĮº
    -0.29
     ties
    -0.28
    åĽĽå¤§
    -0.27
    çļ®
    -0.27
    ç³»
    -0.27
    ä¸Ģ
    -0.26
    åĮħ
    -0.26
    æľŁ
    -0.26
    çĹħ
    -0.26
    éné
    -0.25
    POSITIVE LOGITS
    lop
    0.28
     expression
    0.28
    å±ķæ¼Ķ
    0.28
     rematch
    0.28
     iteration
    0.27
    ByVersion
    0.27
     echo
    0.27
     dispenser
    0.26
     modification
    0.25
    figcaption
    0.25
    Activations Density 0.009%

    No Known Activations