© 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. 57997
    Prev
    Next
    INDEX
    Explanations

    alternating

    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
    ndl
    -0.28
     ÑĤеле
    -0.28
     Contents
    -0.26
    ät
    -0.26
    voice
    -0.25
    -content
    -0.25
     sü
    -0.25
    çŃĮ
    -0.25
    .getContent
    -0.24
    pek
    -0.24
    POSITIVE LOGITS
    缸éĤ»
    0.39
    é¢Ĺ
    0.34
     adjacent
    0.33
    æľĢåIJİä¸Ģ个
    0.33
    第ä¸ī个
    0.33
    éļĶå£ģ
    0.33
    ä¸Ģ个个
    0.33
    第ä¸Ģ个
    0.32
     rows
    0.31
     cells
    0.30
    Activations Density 0.001%

    No Known Activations