© 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. 18-TRANSCODER-HP
    7. 89015
    Prev
    Next
    INDEX
    Explanations

    elections and voting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦçŁ¥è¯Ĩ
    -0.33
    bü
    -0.31
    票
    -0.29
    æŀª
    -0.28
     registr
    -0.27
    ulen
    -0.26
    æ§į
    -0.26
    交æİ¥
    -0.26
    åĴĮå¹³
    -0.25
    iloc
    -0.25
    POSITIVE LOGITS
    寨
    0.27
     trans
    0.25
    ialized
    0.25
    çĬ¯
    0.25
    äºĭ
    0.24
    èĬĤ
    0.24
     Fortress
    0.23
    ties
    0.23
    bidden
    0.23
     alf
    0.23
    Activations Density 4.068%

    No Known Activations