© 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. 141176
    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
    å®Ī
    -0.30
    è¯ħ
    -0.27
    æķıæĦŁ
    -0.26
    Berry
    -0.25
    ä¼łç»ŁçļĦ
    -0.25
    VP
    -0.25
    vp
    -0.24
    çī¹åĪ«æĺ¯
    -0.24
     insensitive
    -0.24
    çĥ
    -0.24
    POSITIVE LOGITS
    èĩĢ
    0.25
     merg
    0.24
    rance
    0.24
    çİ»
    0.24
    naire
    0.24
    gone
    0.23
    éĢĻ次
    0.23
    å®ī举
    0.23
    ---č↵
    0.23
    hoot
    0.23
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.