© 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. 30-TRANSCODER-HP
    7. 96218
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omencl
    -0.27
     entries
    -0.26
    yssey
    -0.25
    CONS
    -0.24
    åºĨç¥Ŀ
    -0.24
    orro
    -0.24
     ÃŃ
    -0.24
    (NAME
    -0.24
    esium
    -0.23
    å°Ħ
    -0.23
    POSITIVE LOGITS
    ยว
    0.27
    å¸Ĥåľºç«ŀäºī
    0.25
    adden
    0.25
    pine
    0.25
     harmed
    0.25
    ä¸»å¼ł
    0.25
    责任åĪ¶
    0.24
    cla
    0.24
    计è¾ĥ
    0.24
    vince
    0.23
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.