© 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. 54410
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     âĨĴ↵↵
    -0.30
    .wikipedia
    -0.28
    ucchini
    -0.27
    ocrat
    -0.27
    lli
    -0.26
    perimental
    -0.26
     —↵↵
    -0.26
    交æį¢
    -0.25
    ctal
    -0.25
    medium
    -0.24
    POSITIVE LOGITS
    à¹Ĥà¸ŀ
    0.27
     primarily
    0.26
     censor
    0.25
    Insets
    0.25
     divor
    0.25
    orm
    0.25
    _MISS
    0.25
     resign
    0.24
    Òĵ
    0.24
    å·¥ä½ľå²Ĺä½į
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.