© 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. 130208
    Prev
    Next
    INDEX
    Explanations

    Countries and cities

    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
    sted
    -0.28
    ror
    -0.28
    orarily
    -0.26
    ä¸ŃçļĦ
    -0.26
    ä¸įåĬ¨
    -0.25
    代
    -0.25
     Hunter
    -0.24
    par
    -0.24
    wij
    -0.24
    fully
    -0.24
    POSITIVE LOGITS
    æŃ¤æ¬¡æ´»åĬ¨
    0.27
    èµ°ç§ģ
    0.26
     hostages
    0.25
    å¥ĩ迹
    0.25
    Released
    0.24
    éĥ½æ²¡
    0.24
     scram
    0.24
    é£İæĥħ
    0.24
     Airlines
    0.23
    就没
    0.23
    Activations Density 10.572%

    No Known Activations