© 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. 128991
    Prev
    Next
    INDEX
    Explanations

    future

    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
    aÄŁ
    -0.27
    isan
    -0.27
    ä¸įå¦Ĥ
    -0.26
    æIJ¬åĪ°
    -0.26
     pals
    -0.26
    ç½ijé¦ĸ页
    -0.25
    rai
    -0.24
    fusc
    -0.24
    MSC
    -0.24
    nant
    -0.24
    POSITIVE LOGITS
     lifetime
    0.28
     battle
    0.27
    arious
    0.27
    ulong
    0.27
    æķħäºĭ
    0.26
    onde
    0.26
     pad
    0.26
     fate
    0.25
     Republic
    0.25
    iro
    0.25
    Activations Density 0.005%

    No Known Activations