© 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. 31-TRANSCODER-HP
    7. 18964
    Prev
    Next
    INDEX
    Explanations

    corporate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¬åı¸
    -0.38
    company
    -0.36
     company
    -0.36
    家åħ¬åı¸
    -0.34
    åħ¬åı¸å°Ĩ
    -0.34
    çļĦä¼ģä¸ļ
    -0.33
    åħ¬åı¸çļĦ
    -0.33
     empresa
    -0.33
    .Company
    -0.33
     Empresa
    -0.33
    POSITIVE LOGITS
    wik
    0.28
    rror
    0.27
    ror
    0.27
    MAND
    0.25
     wik
    0.25
    ocular
    0.24
     correctness
    0.24
    形象
    0.24
    <Image
    0.23
    ugen
    0.23
    Activations Density 0.006%

    No Known Activations