© 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. 53632
    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
     Lockheed
    -0.26
    rames
    -0.25
    nick
    -0.25
    EXPECT
    -0.24
     angle
    -0.24
     Stall
    -0.23
    AdapterManager
    -0.23
    ImageView
    -0.23
    enÃŃ
    -0.23
    -ahead
    -0.23
    POSITIVE LOGITS
     wor
    0.28
    .cursor
    0.27
    è¿Ļ两ç§į
    0.26
    phia
    0.26
    scale
    0.25
    éĺ¶
    0.25
    Dual
    0.24
    å¾ģ
    0.24
    _dual
    0.24
     scale
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.