© 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. 19-TRANSCODER-HP
    7. 9172
    Prev
    Next
    INDEX
    Explanations

    scientific or technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪijçĪ±ä½ł
    -0.26
     wiki
    -0.26
    ABS
    -0.26
     ר×IJש×ķף
    -0.26
    abs
    -0.25
     Sul
    -0.24
    ãģĹãģ¾ãģĨ
    -0.24
    viz
    -0.24
    icos
    -0.23
     (£
    -0.23
    POSITIVE LOGITS
    ä»Ģä¹Īä¸ľè¥¿
    0.35
     unknown
    0.33
     unspecified
    0.33
     behind
    0.33
    æľªçŁ¥
    0.31
     beyond
    0.28
    æŁIJç§į
    0.28
     scrambled
    0.28
     whatever
    0.28
     something
    0.27
    Activations Density 0.185%

    No Known Activations