© 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. 56403
    Prev
    Next
    INDEX
    Explanations

    Zo

    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
    xsd
    -0.26
    abler
    -0.25
     cherry
    -0.25
     ann
    -0.25
    ãĥ¯ãĥ¼
    -0.24
    æĬ½
    -0.24
     torchvision
    -0.24
     lodge
    -0.23
    ulos
    -0.23
    eras
    -0.23
    POSITIVE LOGITS
     requirement
    0.26
    éªĹåŃIJ
    0.25
    åĿĢ
    0.25
    _require
    0.24
     limitation
    0.24
    æķĪ
    0.24
    讲究
    0.24
    Requirement
    0.23
     ErrorMessage
    0.23
    _GU
    0.23
    Activations Density 0.137%

    No Known Activations