© 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. 129899
    Prev
    Next
    INDEX
    Explanations

    Washington

    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
    afa
    -0.29
    atters
    -0.26
     physic
    -0.26
    achi
    -0.25
    ahl
    -0.25
    aptor
    -0.25
    è¿Ļç§į
    -0.24
    isha
    -0.24
    achel
    -0.24
    viewport
    -0.24
    POSITIVE LOGITS
    èĢģ大
    0.28
    sing
    0.27
    æIJŃ
    0.26
    VB
    0.25
    Transpose
    0.25
    duit
    0.25
    hic
    0.24
    s
    0.24
    æIJŃ建
    0.24
    äºİæѤ
    0.23
    Activations Density 6.852%

    No Known Activations