© 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. 52718
    Prev
    Next
    INDEX
    Explanations

    Text snippets and definitions

    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
    åĢĴ
    -0.28
    dot
    -0.28
    igung
    -0.26
    /sites
    -0.25
     wag
    -0.25
    ANDLE
    -0.25
    åĬ¿
    -0.25
     nid
    -0.25
    nid
    -0.24
    -util
    -0.24
    POSITIVE LOGITS
     Creatures
    0.28
    éŁª
    0.27
    人æ°ij
    0.26
     semif
    0.26
    çĭ¬è§Ĵ
    0.25
    çĤ¸å¼¹
    0.24
     Seymour
    0.24
     Elim
    0.24
    \d
    0.24
     Rays
    0.24
    Activations Density 0.041%

    No Known Activations