© 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. 63501
    Prev
    Next
    INDEX
    Explanations

    food, water, safety

    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
     Raised
    -0.30
    Raised
    -0.28
    afil
    -0.27
    /Area
    -0.27
    Heat
    -0.26
     scrap
    -0.26
    .cloudflare
    -0.26
    çĻ¾ä¸ĩ
    -0.25
    Scaler
    -0.24
    phe
    -0.24
    POSITIVE LOGITS
    utes
    0.28
    åľ¨ä¸ĢæĹģ
    0.25
     wake
    0.25
     waking
    0.24
    unik
    0.24
    rite
    0.24
    åºĶæľīçļĦ
    0.24
     ØŃÙĤ
    0.24
    unders
    0.24
    lates
    0.23
    Activations Density 22.232%

    No Known Activations