© 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. 18-TRANSCODER-HP
    7. 89591
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ped
    -0.29
    ç½ļ
    -0.29
    SP
    -0.28
     Ped
    -0.27
    izziness
    -0.27
    suming
    -0.25
    æĸ¹å¼ı
    -0.25
    CRET
    -0.25
     ped
    -0.25
    “We
    -0.25
    POSITIVE LOGITS
    ients
    0.30
     пÑĢоÑĤ
    0.26
    éķĿ
    0.26
    =sc
    0.25
    ylon
    0.25
    nish
    0.25
    æ´
    0.25
    iams
    0.23
    art
    0.23
    .bd
    0.23
    Activations Density 4.617%

    No Known Activations

    This feature has no known activations.