© 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. 4940
    Prev
    Next
    INDEX
    Explanations

    Computer code

    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
    .hm
    -0.28
    æĸ°è¥¿
    -0.27
    ught
    -0.27
    åħ¬ç¤¾
    -0.26
    åĨįçĶŁ
    -0.26
    attern
    -0.26
     barg
    -0.25
    onical
    -0.25
    SetUp
    -0.25
    _unset
    -0.24
    POSITIVE LOGITS
     thôi
    0.28
    éĥ¢
    0.27
    æŁ¢
    0.26
    zers
    0.26
    èĥľè´Ł
    0.25
    ubo
    0.25
    eat
    0.25
     SelectListItem
    0.25
    èĢĮå·²
    0.24
    æł·å¼ı
    0.24
    Activations Density 0.030%

    No Known Activations