© 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. 88161
    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
    å±ħ
    -0.31
    ç»ĦåIJĪ
    -0.28
    é¦Ļ
    -0.28
    æĿ¡ä»¶
    -0.27
     gonna
    -0.26
    )+(
    -0.26
    endphp
    -0.26
    æ°¸è¿ľ
    -0.26
    深深
    -0.25
    chio
    -0.25
    POSITIVE LOGITS
     Lanc
    0.30
    onto
    0.28
    ranges
    0.28
    actories
    0.26
    actory
    0.25
     lanc
    0.25
     breached
    0.25
     DPI
    0.24
    flu
    0.24
    indexed
    0.24
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.