© 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. 142336
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts

    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
    常å§Ķ
    -0.27
    herits
    -0.27
    绶
    -0.25
    ingham
    -0.24
    +]
    -0.24
    åľ°
    -0.24
    éªij
    -0.24
    å©Ģ
    -0.24
    æű
    -0.24
    ital
    -0.23
    POSITIVE LOGITS
    ilver
    0.25
    _quant
    0.25
    rv
    0.25
    rze
    0.25
    æIJ
    0.25
    ÙĪØ®
    0.24
     govern
    0.24
    åĤµåĭĻ
    0.24
    ä¸Ģ代
    0.24
    gle
    0.23
    Activations Density 10.430%

    No Known Activations