© 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. 141630
    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
    dish
    -0.29
     deser
    -0.26
    Alg
    -0.24
    alg
    -0.24
     Lookup
    -0.24
    PLOY
    -0.24
     ThÆ°
    -0.24
    _alg
    -0.23
    åĽł
    -0.23
     vl
    -0.23
    POSITIVE LOGITS
    gı
    0.33
    gué
    0.28
    AndView
    0.27
    é©·
    0.25
    严å¯Ĩ
    0.25
    æīĵå¼ĢäºĨ
    0.25
    adia
    0.25
    tó
    0.25
    ä¸ī大
    0.24
    å°ıå·§
    0.24
    Activations Density 31.504%

    No Known Activations

    This feature has no known activations.