© 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. 108036
    Prev
    Next
    INDEX
    Explanations

    legal documents and names

    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
    .Prot
    -0.28
    ua
    -0.27
     tract
    -0.25
    åĪĽ
    -0.25
     SEC
    -0.25
     tast
    -0.25
    Mem
    -0.25
    omer
    -0.25
    Serial
    -0.24
    è´¹
    -0.24
    POSITIVE LOGITS
    akash
    0.28
     genie
    0.26
    awan
    0.26
     disagreement
    0.26
    cene
    0.25
    =#
    0.25
    cio
    0.24
    缮ãģ«
    0.24
    _sibling
    0.24
     assume
    0.23
    Activations Density 51.316%

    No Known Activations