© 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. 27-TRANSCODER-HP
    7. 8559
    Prev
    Next
    INDEX
    Explanations

    investing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ìĬµ
    -0.28
    æľªæĪIJ
    -0.28
    åķĨåĬ¡
    -0.26
     cylinder
    -0.25
    åIJ¸éĻĦ
    -0.25
     molec
    -0.25
    ç»Ŀ
    -0.24
    _prom
    -0.24
     aide
    -0.24
    oler
    -0.24
    POSITIVE LOGITS
    æĬķèµĦ
    0.54
     investing
    0.53
     investments
    0.53
     investment
    0.51
     invested
    0.50
    çļĦæĬķèµĦ
    0.47
    Invest
    0.46
     Investment
    0.45
     investors
    0.44
     invest
    0.44
    Activations Density 0.033%

    No Known Activations