© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57472
    Prev
    Next
    INDEX
    Explanations

    ignore/ignoring

    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
    Not in Any Lists

    No Comments

    Negative Logits
    IÃĵN
    -0.26
    boxed
    -0.26
     exercised
    -0.25
    eria
    -0.24
    椿
    -0.24
    зв
    -0.24
    caption
    -0.23
     backed
    -0.23
     gunman
    -0.23
    äºĨè¿ĩæĿ¥
    -0.23
    POSITIVE LOGITS
    忽çķ¥
    0.78
     ignore
    0.77
     ignored
    0.75
     neglect
    0.71
     neglected
    0.66
     ignoring
    0.64
    ignore
    0.64
    忽è§Ĩ
    0.63
     IGNORE
    0.61
     Ignore
    0.60
    Activations Density 0.003%

    No Known Activations