© 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. 22-TRANSCODER-HP
    7. 129632
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    recent
    -0.28
    effects
    -0.27
    æĺ¾çĦ¶æĺ¯
    -0.26
     chai
    -0.26
     accustomed
    -0.26
     recently
    -0.25
    'o
    -0.25
    æĺ¾çĦ¶
    -0.24
    åį°è±¡
    -0.24
     lately
    -0.24
    POSITIVE LOGITS
    dna
    0.29
    éļ¶å±ŀ
    0.28
     DNA
    0.27
    幸
    0.27
     dna
    0.26
     methodName
    0.26
     ferment
    0.25
    çĶŁæĪIJ
    0.25
     supers
    0.25
    åĿļåĽº
    0.24
    Activations Density 0.001%

    No Known Activations