© 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. 130290
    Prev
    Next
    INDEX
    Explanations

    Starting, opening, creating things

    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
    eries
    -0.27
     Mahar
    -0.25
     rekl
    -0.24
     wishlist
    -0.24
    审议
    -0.24
    decor
    -0.24
    åıijçĶŁåıĺåĮĸ
    -0.24
    éĢģè´§
    -0.24
    ERY
    -0.23
    ery
    -0.23
    POSITIVE LOGITS
     mind
    0.27
     FIG
    0.25
    为æĬĵ
    0.24
    uitar
    0.24
    bie
    0.24
     Q
    0.24
     habits
    0.24
     PS
    0.24
    èĥ½æĬĬ
    0.24
     bl
    0.24
    Activations Density 9.392%

    No Known Activations