© 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. 6339
    Prev
    Next
    INDEX
    Explanations

    problems

    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
    -exclusive
    -0.29
    åıªä¸º
    -0.27
     established
    -0.27
    à¸ļà¸Ĺ
    -0.26
    å¹ķ
    -0.26
     an
    -0.24
     forall
    -0.24
     measurement
    -0.24
    主ä¹īèĢħ
    -0.24
     functions
    -0.24
    POSITIVE LOGITS
     kino
    0.27
    xDA
    0.26
    LOS
    0.26
    èĥ¸éĥ¨
    0.26
    èĥ¸
    0.26
     MPU
    0.26
     uden
    0.25
    éľ°
    0.25
    PNG
    0.25
    пÑĥ
    0.25
    Activations Density 0.034%

    No Known Activations