© 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. 57558
    Prev
    Next
    INDEX
    Explanations

    scientific abstracts

    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
    æĪijä¸įçŁ¥éģĵ
    -0.32
    xz
    -0.27
    项
    -0.27
     Phát
    -0.27
     gays
    -0.26
    大åıij
    -0.26
    Away
    -0.26
    zend
    -0.25
    æľºèĥ½
    -0.25
    iar
    -0.25
    POSITIVE LOGITS
     Epidemi
    0.30
     Transcript
    0.29
    寡
    0.28
     transcript
    0.28
    ä¸Ģ段
    0.27
    otyping
    0.26
     epidemi
    0.26
    urat
    0.25
     CPI
    0.25
     Ply
    0.24
    Activations Density 0.113%

    No Known Activations