© 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. 57779
    Prev
    Next
    INDEX
    Explanations

    .facebook

    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
    ç«ŀ
    -0.31
     Highlights
    -0.29
     anti
    -0.29
    æѧ
    -0.28
    åľĪ
    -0.27
     Ott
    -0.27
     ant
    -0.27
    空çĻ½
    -0.26
     su
    -0.26
    çĵ¦
    -0.26
    POSITIVE LOGITS
    ä¸İåıijå±ķ
    0.31
    .cons
    0.27
    |#
    0.27
    åĨķ
    0.26
     accr
    0.26
    è¿IJèIJ¥ç®¡çIJĨ
    0.26
    æľ¬æĽ¸
    0.26
    nets
    0.26
    emean
    0.25
    æĪij说
    0.25
    Activations Density 0.004%

    No Known Activations