© 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. 6220
    Prev
    Next
    INDEX
    Explanations

    Secret

    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
    suppress
    -0.26
    POR
    -0.26
    askan
    -0.26
    -initialized
    -0.25
    /GPL
    -0.24
    MMdd
    -0.24
    ventus
    -0.24
    NCY
    -0.24
     ...)↵
    -0.24
    antar
    -0.24
    POSITIVE LOGITS
    ing
    0.28
    没ä»Ģä¹Ī
    0.27
    ä¸įå¤Ł
    0.27
    rect
    0.26
    ugs
    0.25
    è¿ĺä¸įå¤Ł
    0.25
    usal
    0.24
    _caps
    0.24
     nobody
    0.24
    没åħ³ç³»
    0.24
    Activations Density 0.104%

    No Known Activations