© 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. 8905
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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
    æĸĩåŃĹ
    -0.27
    åĢŁè´·
    -0.27
    amped
    -0.27
    æĸĩæľ¬
    -0.27
    OMP
    -0.26
     text
    -0.26
    纲
    -0.25
    é³Į
    -0.25
    iert
    -0.25
    RITE
    -0.25
    POSITIVE LOGITS
    oplay
    0.26
    æĺ¯ä¸Ģ
    0.26
    æĺ¯ä¸Ģ个
    0.25
    oufl
    0.25
    Ñģка
    0.25
    anning
    0.24
    BEGIN
    0.24
    ara
    0.24
    æĪij们ä¸Ģèµ·
    0.24
     reality
    0.24
    Activations Density 0.001%

    No Known Activations