© 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. 20-TRANSCODER-HP
    7. 64381
    Prev
    Next
    INDEX
    Explanations

    Jr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plural
    -0.28
    次æķ°
    -0.27
    plural
    -0.27
    æĨij
    -0.24
     jars
    -0.23
    ãģĤãĤĮ
    -0.23
    SCAN
    -0.23
     getDescription
    -0.23
    ä¸Ģæł·
    -0.23
    ä½ĵ积
    -0.23
    POSITIVE LOGITS
    ime
    0.31
     Hobby
    0.26
    åĽŃ
    0.25
    ull
    0.24
    isme
    0.24
    AMS
    0.24
     AMS
    0.24
     nob
    0.24
    egov
    0.24
    ivial
    0.24
    Activations Density 5.399%

    No Known Activations