© 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. 8879
    Prev
    Next
    INDEX
    Explanations

    variations of "also"

    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
    (AF
    -0.27
    iture
    -0.24
    ë¹Į
    -0.24
    çļĦä¸Ģåijĺ
    -0.24
    åįıä¼ļä¼ļåijĺ
    -0.23
    æŁ¥çľĭåħ¨æĸĩ
    -0.23
     Ã¶ÄŁ
    -0.23
    .unwrap
    -0.23
    ç¯
    -0.23
    ersh
    -0.23
    POSITIVE LOGITS
     also
    1.12
    also
    0.96
    ä¹Ł
    0.86
     Also
    0.83
    Also
    0.80
     juga
    0.74
     ÑĤакже
    0.69
     también
    0.69
    ä¹Łåľ¨
    0.69
    ä¹Łè¦ģ
    0.68
    Activations Density 0.006%

    No Known Activations