© 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. 56791
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æľīæŶ
    -0.84
    æľīæŶåĢĻ
    -0.80
     occasionally
    -0.78
    åĩłæ¬¡
    -0.77
    ç»ı常
    -0.75
     sometimes
    -0.74
     frequently
    -0.73
    æľīä¸Ģ次
    -0.72
     times
    -0.68
    次æķ°
    -0.68
    POSITIVE LOGITS
     Bundy
    0.25
    com
    0.25
    past
    0.25
    ndo
    0.25
    ä¸ĢäºĽ
    0.24
    å¸Ń
    0.24
    宾客
    0.24
     spot
    0.24
    oders
    0.24
    ä¸Ģæĸ¹
    0.24
    Activations Density 0.000%

    No Known Activations