© 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. 129300
    Prev
    Next
    INDEX
    Explanations

    get

    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
    æĪIJ交
    -0.26
    å¼Ģè¾Ł
    -0.25
    è¾Ł
    -0.25
    强度
    -0.25
    osphere
    -0.25
    ä¸įåºĶ该
    -0.25
    uzzle
    -0.24
    iphery
    -0.24
    iveau
    -0.24
    alen
    -0.24
    POSITIVE LOGITS
     studs
    0.27
     Boom
    0.27
     fs
    0.25
    CLS
    0.25
     Hearts
    0.25
    趴
    0.24
     claws
    0.24
    annis
    0.23
     redundancy
    0.23
    IRS
    0.23
    Activations Density 19.517%

    No Known Activations