© 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
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 5126
    Prev
    Next
    INDEX
    Explanations

    Code and forum-like content

    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
     !_
    -0.27
    tract
    -0.27
     PMC
    -0.26
    cluding
    -0.26
    stract
    -0.25
    olics
    -0.25
    á»§a
    -0.24
    .Clone
    -0.24
    suming
    -0.24
    jury
    -0.24
    POSITIVE LOGITS
    pei
    0.27
    æŃ¤ç±»
    0.25
    eg
    0.25
    èĩ³äºİ
    0.24
     eg
    0.24
     inf
    0.24
    enden
    0.23
     SOCKET
    0.23
    (norm
    0.23
    çĥ
    0.23
    Activations Density 0.221%

    No Known Activations