© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 108761
    Prev
    Next
    INDEX
    Explanations

    start

    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
    Negative Logits
    inine
    -0.26
    å¥Ħ
    -0.25
    pect
    -0.24
    ÑģÑĤÑĥп
    -0.24
    ằ
    -0.24
    èĪ¹ä¸Ĭ
    -0.24
     Accum
    -0.24
    车ä¸Ĭ
    -0.24
     Asset
    -0.24
    çİ°çĬ¶
    -0.24
    POSITIVE LOGITS
    eced
    0.24
    å½ĵåĪĿ
    0.24
    è£ħéħįå¼ı
    0.24
    åłĮ
    0.23
    ç¼
    0.23
    vertis
    0.23
    isci
    0.23
    âĹ¡
    0.22
    ifes
    0.22
     Originally
    0.22
    Activations Density 7.447%

    No Known Activations