© 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. 30-TRANSCODER-HP
    7. 95748
    Prev
    Next
    INDEX
    Explanations

    Intentionality

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ump
    -0.24
    /*================================================================
    -0.24
    rist
    -0.24
    é¦ģ
    -0.23
    MenuStrip
    -0.23
    lore
    -0.23
    æĸ¥
    -0.23
     ort
    -0.23
     Inspector
    -0.23
    ç°¿
    -0.23
    POSITIVE LOGITS
     purpose
    1.45
     intentional
    1.36
     intentionally
    1.29
    æľīæĦı
    1.22
    æķħæĦı
    1.21
    purpose
    1.20
     intention
    1.20
     Purpose
    1.19
     deliberate
    1.18
     deliberately
    1.14
    Activations Density 0.998%

    No Known Activations