© 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. 142236
    Prev
    Next
    INDEX
    Explanations

    to

    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
    å¾Ĵ
    -0.27
    åĻ¨åħ·
    -0.26
    nen
    -0.26
    主ä¹īæĢĿæĥ³
    -0.26
    æĥ³æ³ķ
    -0.25
    寻æ±Ĥ
    -0.25
    æ¿Ĵ临
    -0.25
    鬣
    -0.25
    åħĢ
    -0.25
    è¯ķåĽ¾
    -0.25
    POSITIVE LOGITS
    olate
    0.26
    words
    0.25
    -upper
    0.25
    perse
    0.24
    ubbo
    0.24
    elpers
    0.24
    lass
    0.24
    WORDS
    0.24
    ircon
    0.24
    ä¸įæĩĪ
    0.24
    Activations Density 14.330%

    No Known Activations