© 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. 27-TRANSCODER-HP
    7. 8250
    Prev
    Next
    INDEX
    Explanations

    symptoms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vÃŃ
    -0.27
    batis
    -0.27
    sic
    -0.25
    åīª
    -0.25
    etat
    -0.25
    illary
    -0.24
    æĸ¹å½¢
    -0.24
     virtual
    -0.24
    om
    -0.24
    erialize
    -0.24
    POSITIVE LOGITS
    median
    0.27
    sov
    0.26
    sono
    0.26
    çħ
    0.25
     <<=
    0.25
     toasted
    0.24
     lasting
    0.24
    ç¥
    0.24
    inks
    0.23
    ä»ħ代表
    0.23
    Activations Density 0.054%

    No Known Activations