© 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. 53649
    Prev
    Next
    INDEX
    Explanations

    addresses and locations

    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
    iei
    -0.27
     kB
    -0.25
     Rosenberg
    -0.24
    ie
    -0.24
     Pale
    -0.23
     Higgins
    -0.23
    [h
    -0.22
     B
    -0.22
    okit
    -0.22
    ừ
    -0.22
    POSITIVE LOGITS
    Live
    0.30
     Live
    0.27
    æĿŁ
    0.26
     live
    0.25
    edar
    0.25
    ecera
    0.25
    live
    0.24
    pas
    0.24
    Living
    0.24
    ertas
    0.24
    Activations Density 0.012%

    No Known Activations