© 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. 57932
    Prev
    Next
    INDEX
    Explanations

    ï¼ļ

    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
    液
    -0.31
    qualities
    -0.28
     award
    -0.28
     Nil
    -0.26
    éĽĮ
    -0.25
     strongly
    -0.25
    åħ¨ä½ĵåijĺå·¥
    -0.24
    ħ§
    -0.24
    æĪĸ许
    -0.24
    é²ľæ´»
    -0.24
    POSITIVE LOGITS
    ucket
    0.27
    好转
    0.27
    æij¹
    0.26
    belongs
    0.26
    lemen
    0.25
    ä¸įèĩ³äºİ
    0.25
    urable
    0.24
    nodoc
    0.24
    .utcnow
    0.24
    æĹ¥åľ¨
    0.24
    Activations Density 0.001%

    No Known Activations