© 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. 88665
    Prev
    Next
    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    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
    ÙħÙĨ
    -0.29
     Sof
    -0.27
    éĢĿ
    -0.26
     condemning
    -0.25
    è´¸
    -0.24
    çĹħ
    -0.24
    fiber
    -0.24
    -ts
    -0.24
    尤为éĩįè¦ģ
    -0.24
    isChecked
    -0.24
    POSITIVE LOGITS
    http
    0.27
    个å°ı
    0.27
    çļĦä¸ĢéĿ¢
    0.25
    ierge
    0.25
    åĸľ
    0.24
     triple
    0.24
    ederland
    0.24
    kn
    0.24
    olut
    0.24
     inner
    0.23
    Activations Density 35.789%

    No Known Activations