© 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. 20-TRANSCODER-HP
    7. 63248
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç»ķ
    -0.31
    åīįæĻ¯
    -0.27
    æĹłåĬ©
    -0.26
    ç¹ŀ
    -0.25
    asics
    -0.24
    帮
    -0.24
    ivered
    -0.24
    andel
    -0.24
     Saved
    -0.24
    ritch
    -0.24
    POSITIVE LOGITS
    çĽĨåľ°
    0.28
    shal
    0.28
    å®
    0.28
    çĶŁæ´»ä¹łæĥ¯
    0.26
     caffe
    0.26
    ç¦ģåĮº
    0.25
    juan
    0.25
     tent
    0.25
     camper
    0.25
    over
    0.24
    Activations Density 6.637%

    No Known Activations

    This feature has no known activations.