© 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. 22-TRANSCODER-HP
    7. 131192
    Prev
    Next
    INDEX
    Explanations

    technology and industry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ¦ľ
    -0.26
    обоÑĢоÑĤ
    -0.26
    -fed
    -0.24
     suites
    -0.23
    æľ¬èĥ½
    -0.23
    Ñİ
    -0.23
     вÑĭпÑĥÑģ
    -0.23
    _SLOT
    -0.23
    æ¶ħ
    -0.22
     Rule
    -0.22
    POSITIVE LOGITS
    ,âĢ¦↵↵
    0.27
    ective
    0.25
    âĢ¦↵↵↵↵
    0.25
    $p
    0.24
    ãĤ¢ãĤ¦
    0.24
    onium
    0.23
    TU
    0.23
    ãĥ³ãĤ°
    0.23
    <quote
    0.23
    ï¼ģ↵↵↵↵
    0.23
    Activations Density 0.070%

    No Known Activations