© 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. 32-TRANSCODER-HP
    7. 41340
    Prev
    Next
    INDEX
    Explanations

    food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cape
    -0.26
    upt
    -0.25
    arty
    -0.24
    simd
    -0.24
    ingle
    -0.24
    .crm
    -0.23
    izo
    -0.23
    licos
    -0.23
    illé
    -0.23
     ÑģоÑħ
    -0.23
    POSITIVE LOGITS
     food
    1.43
    food
    1.27
    é£Łçī©
    1.25
     Food
    1.18
    Food
    1.16
    é£Łåĵģ
    1.13
    -food
    1.07
    _food
    1.04
    é£Ł
    1.04
    çļĦé£Łçī©
    1.01
    Activations Density 0.003%

    No Known Activations