© 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. 64665
    Prev
    Next
    INDEX
    Explanations

    know

    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
    ç§Ń
    -0.29
    /MIT
    -0.28
    è¾Ħ
    -0.27
     Parameter
    -0.26
    eyed
    -0.25
    éļ¾
    -0.24
    çļĦ缮çļĦ
    -0.24
    vasion
    -0.24
     меÑģÑĤа
    -0.24
    ees
    -0.23
    POSITIVE LOGITS
    matter
    0.27
    rone
    0.26
     anchor
    0.25
    constitutional
    0.25
     constitutional
    0.25
     matter
    0.24
     though
    0.24
    haps
    0.24
    though
    0.23
     Devil
    0.23
    Activations Density 10.857%

    No Known Activations