© 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. 142560
    Prev
    Next
    INDEX
    Explanations

    Magazines and reviews

    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
    hn
    -0.25
    æŁIJç§į
    -0.25
    nickname
    -0.24
    ive
    -0.24
    aram
    -0.24
    ä¸ĬçļĦ
    -0.24
    Gb
    -0.24
    ToStr
    -0.24
     Mein
    -0.23
    ìłģ
    -0.23
    POSITIVE LOGITS
    elin
    0.34
    è¶Ĭ
    0.27
    leys
    0.26
    olon
    0.25
     invested
    0.25
    >Delete
    0.24
    çIJĨæĢ§
    0.24
    inceton
    0.24
     Bog
    0.23
    è¸Ĭè·ĥ
    0.23
    Activations Density 0.267%

    No Known Activations