© 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. 141272
    Prev
    Next
    INDEX
    Explanations

    Coherent English text

    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
     warmth
    -0.33
    æ°Ķ温
    -0.30
     Mood
    -0.29
     warming
    -0.28
    æĢģ度
    -0.27
    å¿ĥæĥħ
    -0.27
    温
    -0.27
    æļij
    -0.27
    çļĦå¿ĥæĥħ
    -0.26
    温æļĸ
    -0.26
    POSITIVE LOGITS
    æŀľæłij
    0.29
     size
    0.29
    åĪ©åĻ¨
    0.28
    ony
    0.28
    ä¸Ńç§ij
    0.28
    éĵ¾
    0.28
    ä»Ģä¹Īä¸ľè¥¿
    0.27
    å¹³åı°ä¸Ĭ
    0.27
    .platform
    0.27
     sizes
    0.26
    Activations Density 80.180%

    No Known Activations