© 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. 141515
    Prev
    Next
    INDEX
    Explanations

    mean

    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
     testim
    -0.27
    ourcing
    -0.27
    cae
    -0.27
    olie
    -0.27
    noch
    -0.26
    çįIJ
    -0.26
    MethodManager
    -0.25
    UIT
    -0.24
    /cgi
    -0.24
    é¼ĵèĪŀ
    -0.24
    POSITIVE LOGITS
     size
    0.27
    åĪĩå®ŀ
    0.25
     indices
    0.25
    irection
    0.24
     devis
    0.24
    ajes
    0.24
    课
    0.24
     ë
    0.23
    ura
    0.23
     developer
    0.23
    Activations Density 2.528%

    No Known Activations