© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162771
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Compensation
    -0.27
    _RW
    -0.26
    .hl
    -0.25
    Issues
    -0.25
    å·¥ä½ľæĬ¥åijĬ
    -0.24
    è§Ĵ度çľĭ
    -0.24
    daf
    -0.24
     compensation
    -0.24
     pyt
    -0.23
    ä¸Ģäºĭ
    -0.23
    POSITIVE LOGITS
     streak
    0.32
    аÑģ
    0.27
    èĪį
    0.26
     cann
    0.26
    Bell
    0.26
    éĵİ
    0.25
    éĸ
    0.25
    ét
    0.24
    oute
    0.24
    :o
    0.24
    Activations Density 0.058%

    No Known Activations

    This feature has no known activations.