© 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. 108335
    Prev
    Next
    INDEX
    Explanations

    ia

    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
    enberg
    -0.27
    gre
    -0.26
    eg
    -0.26
    .story
    -0.26
    æĦı大
    -0.24
     cond
    -0.23
    &S
    -0.23
    鬻
    -0.23
    reopen
    -0.23
     advant
    -0.23
    POSITIVE LOGITS
     hyp
    0.28
    游
    0.25
    quals
    0.25
    kah
    0.25
    IRO
    0.25
    arness
    0.24
    ughs
    0.24
    æ¸ħç®Ĺ
    0.24
    å¥ĩå¦Ļ
    0.23
    ĶåĽŀ
    0.23
    Activations Density 16.700%

    No Known Activations