© 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. 18793
    Prev
    Next
    INDEX
    Explanations

    politicians

    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
     sym
    -0.28
    perse
    -0.27
    chez
    -0.27
    tails
    -0.27
     pháºŃn
    -0.26
    .sym
    -0.25
    èµ·äºĨ
    -0.25
     taÅŁÄ±
    -0.24
    cate
    -0.24
    å°Ħæīĭ
    -0.24
    POSITIVE LOGITS
    è¯ķæİ¢
    0.30
    åIJ¯åıij
    0.28
     automat
    0.28
    Fig
    0.27
     Fig
    0.26
     axis
    0.26
     hypoc
    0.26
    èĿł
    0.25
    åıĺ
    0.25
     Institution
    0.25
    Activations Density 0.018%

    No Known Activations