© 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. 20-TRANSCODER-HP
    7. 141616
    Prev
    Next
    INDEX
    Explanations

    There

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otion
    -0.30
    æ²ī
    -0.29
    vented
    -0.27
    èµ·äºĨ
    -0.25
    vents
    -0.25
    esa
    -0.25
    ðŁĵIJ
    -0.25
    Interceptor
    -0.24
    åĩºäºĨ
    -0.23
    ä¸ŃéĢĶ
    -0.23
    POSITIVE LOGITS
    èĩªåѦ
    0.26
    iom
    0.25
    å¼Ĥ
    0.24
    èµĦæºIJåħ±äº«
    0.24
    çļĦ女åŃ©
    0.24
     trÆ°á»Łng
    0.24
    缸åıį
    0.24
     psyched
    0.24
     Tel
    0.23
    صر
    0.23
    Activations Density 19.940%

    No Known Activations