© 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. 25-TRANSCODER-HP
    7. 108858
    Prev
    Next
    INDEX
    Explanations

    places/proper nouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONO
    -0.33
    æĿĥéĻIJ
    -0.25
    çĽĨåľ°
    -0.25
     grat
    -0.25
    UnderTest
    -0.24
    onaut
    -0.24
    coni
    -0.24
     freshly
    -0.23
    dar
    -0.23
     gradients
    -0.23
    POSITIVE LOGITS
    表达
    0.27
     Yad
    0.25
    .BorderFactory
    0.25
    fold
    0.24
    userData
    0.24
     userData
    0.24
     cityName
    0.24
    isman
    0.24
    empl
    0.24
    说åĩº
    0.23
    Activations Density 0.158%

    No Known Activations