© 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. 31-TRANSCODER-HP
    7. 18803
    Prev
    Next
    INDEX
    Explanations

    political

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     practice
    -0.32
     Py
    -0.28
     Practice
    -0.26
    å®ŀè·µ
    -0.26
    uls
    -0.26
     pratique
    -0.26
     practiced
    -0.25
    åıį
    -0.25
    anches
    -0.25
    practice
    -0.25
    POSITIVE LOGITS
    çļĦæĶ¯æĮģ
    0.31
    æłĩè¯Ĩ
    0.28
    åĩ¿
    0.28
    á¸į
    0.28
    好人
    0.27
    avia
    0.27
    ðŁĶİ
    0.26
    æĶ¯æĮģ
    0.26
     views
    0.26
    .Creator
    0.26
    Activations Density 1.980%

    No Known Activations