© 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. 86759
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    Final
    -0.25
    Met
    -0.24
     Passion
    -0.23
    æĮĩæĮ¥
    -0.23
    cards
    -0.23
    Runs
    -0.23
     skilled
    -0.23
    Char
    -0.22
    ä»ĩ
    -0.22
    @"
    -0.22
    POSITIVE LOGITS
    并åıij
    0.27
    Ĥ¬
    0.25
    iteDatabase
    0.25
    æĹ¶è¾°
    0.24
    .sap
    0.24
    ä¸į失
    0.24
    éªĢ
    0.24
    以ä¸ĬçļĦ
    0.23
    çĺ¤
    0.23
     Swe
    0.23
    Activations Density 0.004%

    No Known Activations