© 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. 129898
    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
    Bu
    -0.31
    ridge
    -0.29
     lowest
    -0.28
    (rate
    -0.27
    linger
    -0.27
     zad
    -0.25
    æĸ°äºº
    -0.24
    ’un
    -0.24
    è¾Ľ
    -0.24
    æľŁ
    -0.24
    POSITIVE LOGITS
    æīįèĥ½å¤Ł
    0.27
     summaries
    0.27
    èĩªçĦ¶èĢĮ
    0.25
    çĺĹ
    0.25
     Ord
    0.25
    éħª
    0.24
    ä¾
    0.24
     ord
    0.24
    纪å½ķ
    0.24
    åĽŀé¦Ī
    0.23
    Activations Density 8.183%

    No Known Activations

    This feature has no known activations.