© 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. 53516
    Prev
    Next
    INDEX
    Explanations

    unusual mixed text entries

    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
    long
    -0.32
     long
    -0.29
    éķ¿æľŁ
    -0.28
    pare
    -0.26
    itive
    -0.26
    la
    -0.25
    pas
    -0.25
    IDI
    -0.25
    å¼Ģ
    -0.25
    las
    -0.24
    POSITIVE LOGITS
     Ribbon
    0.29
    ı
    0.25
    è£Ł
    0.25
    ernational
    0.24
    RLF
    0.24
     Hornets
    0.24
     Mounted
    0.24
    MISSION
    0.24
    eon
    0.24
    omial
    0.23
    Activations Density 0.026%

    No Known Activations