© 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. 130377
    Prev
    Next
    INDEX
    Explanations

    wide range of topics

    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
    è¯Ŀ
    -0.26
     (~
    -0.26
    eto
    -0.25
    éģĵçIJĨ
    -0.25
    åī©
    -0.24
    å©Ģ
    -0.24
     Hin
    -0.24
    lobals
    -0.24
     variety
    -0.23
     hook
    -0.23
    POSITIVE LOGITS
    è¿°
    0.26
     tech
    0.26
     Passport
    0.25
    ä¸ĸ纪
    0.25
    åij¨ä¸ī
    0.25
    imes
    0.25
    ç¼ĸ
    0.25
    less
    0.24
     Tech
    0.24
    .infinity
    0.24
    Activations Density 18.970%

    No Known Activations