© 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. 18992
    Prev
    Next
    INDEX
    Explanations

    bubble

    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
    触
    -0.30
     åľ
    -0.29
    åħ»æĪIJ
    -0.28
    åıį
    -0.28
    åŁ¹åħ»
    -0.26
    essay
    -0.26
    èIJ½
    -0.26
    é£Ł
    -0.26
     Reaction
    -0.26
    Drive
    -0.26
    POSITIVE LOGITS
     pip
    0.32
     vibrating
    0.31
    è±IJ
    0.29
    éĽĨåĽ¢èĤ¡ä»½
    0.26
     trần
    0.26
     dil
    0.26
    ocket
    0.25
     unin
    0.25
    มหา
    0.25
    å¾ģæ±ĤæĦıè§ģ
    0.25
    Activations Density 0.046%

    No Known Activations