© 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. 107598
    Prev
    Next
    INDEX
    Explanations

    0

    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
    模æĭŁ
    -0.27
     rooting
    -0.25
    .currentState
    -0.25
    Vac
    -0.25
    .sap
    -0.24
     sede
    -0.24
    åĪĨæµģ
    -0.24
    reed
    -0.24
    estre
    -0.23
    èĮ¸
    -0.23
    POSITIVE LOGITS
    ops
    0.28
    aight
    0.27
    oppers
    0.26
    æĿ¿åĿĹ
    0.26
    å·¦åı³
    0.25
    ort
    0.25
    .setBackground
    0.25
    ppers
    0.25
    BT
    0.24
    Ross
    0.24
    Activations Density 6.395%

    No Known Activations