© 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. 7098
    Prev
    Next
    INDEX
    Explanations

    Descriptive text

    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
     Lo
    -0.28
    utive
    -0.28
    èİĬ
    -0.27
    [âĢ¦
    -0.27
     middle
    -0.27
     ref
    -0.25
    åºĦ
    -0.25
    '+↵
    -0.25
    igans
    -0.25
    å·¨é¢Ŀ
    -0.25
    POSITIVE LOGITS
     Pistol
    0.29
    oundation
    0.29
    ereum
    0.28
    è¿ĺä¸įéĶĻ
    0.27
     dawn
    0.26
     Wik
    0.25
    gie
    0.25
    éŨ
    0.25
    quo
    0.24
    COME
    0.24
    Activations Density 0.011%

    No Known Activations