© 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. 27-TRANSCODER-HP
    7. 7930
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åıijçĥ§
    -0.30
    åŃ£åIJİ
    -0.26
    æľīæĦıæĢĿçļĦ
    -0.25
    éĻ¢åī¯éĻ¢éķ¿
    -0.25
    leases
    -0.25
     commission
    -0.25
    _inactive
    -0.25
    chal
    -0.24
     fclose
    -0.24
     iteration
    -0.24
    POSITIVE LOGITS
    ä¾Ľç»Ļ
    0.34
    rete
    0.28
     recon
    0.27
    otate
    0.26
    ä½ij
    0.25
     appreciated
    0.24
    жи
    0.24
    illery
    0.24
    åĨįéĢł
    0.23
    æłĩçļĦ
    0.23
    Activations Density 0.783%

    No Known Activations