© 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. 24-TRANSCODER-HP
    7. 150936
    Prev
    Next
    INDEX
    Explanations

    medical research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     characterized
    -0.27
    emed
    -0.25
    æĪĸå¤ļ
    -0.25
    guna
    -0.24
    åįķä¸Ģ
    -0.24
    æµĥ
    -0.24
    é£İåij³
    -0.24
    è¡¥
    -0.24
    èĮĥ
    -0.24
    羯
    -0.23
    POSITIVE LOGITS
    aque
    0.27
    iare
    0.26
    -than
    0.26
    ilee
    0.24
    æģ¶æĢ§
    0.24
    赶快
    0.24
     bowed
    0.24
    çģ¾åĮº
    0.23
    brain
    0.23
    ubble
    0.23
    Activations Density 0.090%

    No Known Activations