© 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. 20-TRANSCODER-HP
    7. 63615
    Prev
    Next
    INDEX
    Explanations

    geography/location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    款
    -0.27
    诤
    -0.27
    TAG
    -0.26
    çķĮçļĦ
    -0.25
    tag
    -0.25
    itz
    -0.25
    inas
    -0.25
    unning
    -0.25
    plate
    -0.25
    ambio
    -0.24
    POSITIVE LOGITS
    LOAT
    0.26
    leep
    0.25
     Speedway
    0.25
    åľ°éģĵ
    0.25
    (','
    0.25
     AUTHORS
    0.24
    èµĸ以
    0.24
    prüf
    0.24
    BOOLE
    0.24
     najwiÄĻkszy
    0.24
    Activations Density 2.286%

    No Known Activations