© 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. 7742
    Prev
    Next
    INDEX
    Explanations

    inflammation

    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
    avatars
    -0.27
    åŁİåİ¿
    -0.25
    hand
    -0.24
    robat
    -0.24
    ç»´å°Ķ
    -0.24
     Nodes
    -0.23
    å¸ĤæķĻèĤ²å±Ģ
    -0.23
    untos
    -0.23
    红线
    -0.23
    Nodes
    -0.22
    POSITIVE LOGITS
    缸åħ³
    0.26
    ä¸Ģ声
    0.24
    Submitted
    0.24
    igos
    0.24
    _maximum
    0.23
     maximal
    0.23
    rogen
    0.23
     bomb
    0.23
    wait
    0.22
    .functional
    0.22
    Activations Density 0.804%

    No Known Activations