© 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. 142249
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives

    np_max-act · gemini-2.0-flash
    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
    sWith
    -0.34
    screen
    -0.30
    cheon
    -0.30
    lösung
    -0.28
    eldorf
    -0.27
    æĦģ
    -0.27
    ÂŃtion
    -0.26
     Introduced
    -0.26
    enced
    -0.26
     Miscellaneous
    -0.25
    POSITIVE LOGITS
    -than
    0.42
    éĻIJ度
    0.29
    æĹ¥å¸¸å·¥ä½ľ
    0.28
    _than
    0.26
     exem
    0.25
    adin
    0.25
     ni
    0.25
     than
    0.25
    交ä»ĺ
    0.24
     вÑģего
    0.24
    Activations Density 28.895%

    No Known Activations