© 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. 64011
    Prev
    Next
    INDEX
    Explanations

    outdoors

    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
    .unshift
    -0.27
    elt
    -0.26
    disp
    -0.26
    .lua
    -0.24
    èĥĮ
    -0.24
     Ala
    -0.24
    ancy
    -0.24
    æıIJåĢ¡
    -0.24
     доÑģÑĤ
    -0.23
    pen
    -0.23
    POSITIVE LOGITS
    ignum
    0.26
    ç´¯äºĨ
    0.26
    åħ³æĢĢ
    0.26
     mundane
    0.25
    schemas
    0.25
    icals
    0.25
    ä¸įåĪ°
    0.25
    )set
    0.24
     equipments
    0.24
    è¯ķè¯ķ
    0.24
    Activations Density 5.818%

    No Known Activations