© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6517
    Prev
    Next
    INDEX
    Explanations

    Math and calculations

    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
    å¥Ķ
    -0.27
    ppy
    -0.25
    çĵ¶åŃIJ
    -0.25
    Ùħات
    -0.25
    educt
    -0.24
    åĿĩè¡¡
    -0.24
    æĺŁéĻħ
    -0.23
    FFE
    -0.23
    ÑģÑĤавил
    -0.23
    åĨĻåŃĹ楼
    -0.23
    POSITIVE LOGITS
    æĹłè®ºå¦Ĥä½ķ
    0.26
     coraz
    0.25
    tn
    0.25
    æĤ£
    0.25
     fault
    0.25
    ä¸Ģ个å¤ļæľĪ
    0.25
     PLUS
    0.24
    idades
    0.24
    è®°
    0.24
    âĺº
    0.24
    Activations Density 0.011%

    No Known Activations