© 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. 12-TRANSCODER-HP
    7. 22548
    Prev
    Next
    INDEX
    Explanations

    region

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    临
    -0.28
    -rad
    -0.26
    ziej
    -0.25
     régl
    -0.25
     radix
    -0.25
    ung
    -0.25
    å±ĬæŶ
    -0.25
     hor
    -0.25
    ến
    -0.24
     té
    -0.24
    POSITIVE LOGITS
    ponsored
    0.29
    кÑĥп
    0.27
    Disposition
    0.26
     plan
    0.26
    ç»Ģ
    0.25
     Gün
    0.24
     Mane
    0.24
    FromString
    0.23
    å¹ħ
    0.23
     Latvia
    0.23
    Activations Density 0.011%

    No Known Activations