© 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. 53215
    Prev
    Next
    INDEX
    Explanations

    link

    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
     Civ
    -0.26
    iec
    -0.25
    onen
    -0.24
    å¿Ĺ强
    -0.24
    cratch
    -0.24
    åĨħ容
    -0.24
    鸣
    -0.23
     dáºŃy
    -0.23
    cip
    -0.23
    .ArrayAdapter
    -0.23
    POSITIVE LOGITS
     link
    1.14
     links
    1.07
     linked
    1.05
    link
    1.02
     Link
    1.00
    éĵ¾æİ¥
    0.99
     LINK
    0.98
    -link
    0.96
    links
    0.96
    linked
    0.95
    Activations Density 0.309%

    No Known Activations