© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7027
    Prev
    Next
    INDEX
    Explanations

    Research abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ноÑģÑĤей
    -0.29
    imates
    -0.28
    çĽijçĿ£ç®¡çIJĨ
    -0.25
    污æŁĵ
    -0.25
    èĮ«èĮ«
    -0.24
    ates
    -0.24
    reg
    -0.24
     ya
    -0.24
    structions
    -0.23
     thereof
    -0.23
    POSITIVE LOGITS
    åŃª
    0.30
    pedia
    0.28
    aidu
    0.25
     Jord
    0.25
    UPI
    0.25
    å©¿
    0.25
    /apt
    0.24
     José
    0.23
    osite
    0.23
    绪
    0.23
    Activations Density 0.401%

    No Known Activations