© 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. 141568
    Prev
    Next
    INDEX
    Explanations

    for

    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
    çłĸ
    -0.29
    社ä¼ļ
    -0.27
     --------------------------------------------------------------------------↵
    -0.27
    à¹Ĥà¸Ĭà¸Ħ
    -0.27
    å®ŀä¸ļ
    -0.26
     augmented
    -0.26
    NAS
    -0.26
     NAS
    -0.26
    è¯ļ
    -0.25
    建çŃijä¸ļ
    -0.25
    POSITIVE LOGITS
    htag
    0.29
     withdrawn
    0.27
    orst
    0.26
    bourg
    0.26
    arent
    0.25
    ,strlen
    0.25
     sunk
    0.25
    èĦ±
    0.25
    idable
    0.25
    ledon
    0.24
    Activations Density 60.835%

    No Known Activations