© 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. 63546
    Prev
    Next
    INDEX
    Explanations

    general/various contexts

    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
    lope
    -0.28
    èµ°äºĨ
    -0.27
    itarian
    -0.26
    è·Łè¿Ľ
    -0.26
    uries
    -0.25
    使èĢħ
    -0.25
    åŃĺéĩı
    -0.24
     Moder
    -0.24
    ilities
    -0.24
    egration
    -0.24
    POSITIVE LOGITS
    .tap
    0.28
    rna
    0.26
    rlen
    0.26
    PUT
    0.25
    dü
    0.25
     Scholar
    0.24
     Chairs
    0.24
    ॰
    0.24
    ruz
    0.24
    alborg
    0.23
    Activations Density 16.169%

    No Known Activations