© 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. 22-TRANSCODER-HP
    7. 112284
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     negatives
    -0.27
    讲æķħäºĭ
    -0.26
    ston
    -0.25
    peng
    -0.25
    ecs
    -0.25
    :len
    -0.24
    ungan
    -0.24
     jus
    -0.24
    itives
    -0.24
    hes
    -0.24
    POSITIVE LOGITS
    å¢ŀæĶ¶
    0.27
    太å°ij
    0.25
    æľīçĶ¨
    0.25
    èĶĵ
    0.24
     prof
    0.23
     Strand
    0.23
    Math
    0.23
     screens
    0.23
    Prof
    0.23
     herself
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.