© 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. 23-TRANSCODER-HP
    7. 25368
    Prev
    Next
    INDEX
    Explanations

    creat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ovel
    -0.26
    hood
    -0.26
    hom
    -0.26
    hop
    -0.26
     Fixed
    -0.25
     fixed
    -0.24
    åIJĪä¸Ģ
    -0.24
    etas
    -0.24
     FIXED
    -0.24
    hand
    -0.23
    POSITIVE LOGITS
    è±IJ
    0.26
    ä¸į失
    0.26
    æĻķ
    0.25
    azz
    0.25
    è¿·
    0.25
    ä¸įèµ·
    0.25
    é²ľæĺİ
    0.23
    ours
    0.23
    ypes
    0.23
    elier
    0.23
    Activations Density 0.042%

    No Known Activations