© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53783
    Prev
    Next
    INDEX
    Explanations

    patients

    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
    ças
    -0.30
     med
    -0.29
     cup
    -0.28
    æį»
    -0.28
    -med
    -0.27
     cups
    -0.26
    æĿ¯
    -0.25
     mediation
    -0.25
     artwork
    -0.25
    Dos
    -0.25
    POSITIVE LOGITS
    ä¹Łæĺ¯ä¸Ģ个
    0.28
    inus
    0.27
     possess
    0.26
    _INF
    0.26
    toa
    0.25
     dis
    0.25
    ä¸įæĺ¯ä¸Ģ个
    0.25
     progress
    0.25
    -required
    0.24
     require
    0.23
    Activations Density 0.080%

    No Known Activations