© 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. 9-TRANSCODER-HP
    7. 29099
    Prev
    Next
    INDEX
    Explanations

    is are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    عرب
    -0.31
    tra
    -0.28
    _NS
    -0.27
    tery
    -0.27
    ç¼¥
    -0.26
    èĭ¦
    -0.26
    isto
    -0.25
    Raw
    -0.24
    å®ŀåĬĽ
    -0.24
    èģĮ
    -0.24
    POSITIVE LOGITS
    éĩĩ
    0.30
    ensed
    0.30
    etsk
    0.29
    ikh
    0.28
    indre
    0.27
    é«ĺæ¸ħ
    0.26
    sequ
    0.25
     Gem
    0.25
    ught
    0.24
     gem
    0.24
    Activations Density 1.530%

    No Known Activations