© 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. 6816
    Prev
    Next
    INDEX
    Explanations

    past

    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
    åľ¨è¿ĩ渡
    -0.29
    æĺ§
    -0.26
    èĥ
    -0.25
    GRADE
    -0.25
     Forever
    -0.24
    åľ¨åºĬä¸Ĭ
    -0.24
    æ±°
    -0.24
     Interr
    -0.23
    inium
    -0.23
    eus
    -0.23
    POSITIVE LOGITS
    5
    0.28
     rig
    0.28
    agon
    0.27
    Ñİ
    0.27
    tra
    0.26
     challenge
    0.26
     Sol
    0.26
    1
    0.26
     regular
    0.26
     Hen
    0.26
    Activations Density 0.200%

    No Known Activations