© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7163
    Prev
    Next
    INDEX
    Explanations

    Common suffixes

    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
    AuthProvider
    -0.26
    YPE
    -0.24
    rieb
    -0.24
    berger
    -0.23
    uptools
    -0.22
    ussen
    -0.22
    羡
    -0.22
    zsche
    -0.21
    ières
    -0.21
    popular
    -0.21
    POSITIVE LOGITS
    éĻ¤æѤ
    0.23
    å°±è¿Ļæł·
    0.23
    æĢİä¹Ī说
    0.23
    lings
    0.23
    ä¸ŃåĽ½ç»ıæµİ
    0.23
     nails
    0.22
    RequestBody
    0.22
    å°±åľ¨
    0.21
    ;z
    0.21
    åħ¶å®ŀ
    0.21
    Activations Density 0.060%

    No Known Activations