© 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. 53152
    Prev
    Next
    INDEX
    Explanations

    non-English/code

    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
    igans
    -0.29
    reur
    -0.27
    iped
    -0.27
    ipes
    -0.27
    dance
    -0.27
    mant
    -0.26
    çĩĥ
    -0.26
    IFF
    -0.26
     pan
    -0.26
    út
    -0.26
    POSITIVE LOGITS
    衽
    0.26
    å¤ļå°ijéĴ±
    0.26
    .makeText
    0.25
    arÃŃa
    0.24
    kea
    0.24
    al
    0.23
    elcome
    0.23
     strengthen
    0.23
     conclus
    0.23
    ä¸įåĬ¨
    0.22
    Activations Density 0.005%

    No Known Activations