© 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. 54534
    Prev
    Next
    INDEX
    Explanations

    computing and tech

    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
    ä½ĵä¼ļ
    -0.31
    é«ĺå°ļ
    -0.29
    åį§
    -0.29
    ures
    -0.28
    airs
    -0.27
    çŃ¹èµĦ
    -0.26
    çķľ
    -0.26
     taller
    -0.26
    å¤
    -0.26
    ForResource
    -0.25
    POSITIVE LOGITS
    åĮħåŃIJ
    0.28
    ija
    0.27
    LiveData
    0.26
     beans
    0.26
     bla
    0.25
    ikal
    0.25
    feas
    0.25
    grÃ¶ÃŁe
    0.25
    fea
    0.24
    æĶ¶
    0.24
    Activations Density 0.003%

    No Known Activations