© 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. 22-TRANSCODER-HP
    7. 97834
    Prev
    Next
    INDEX
    Explanations

    Medical and chemical contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nants
    -0.28
    æ¨Ļ
    -0.27
    itag
    -0.26
    Slash
    -0.24
    çijĻ
    -0.24
    ipay
    -0.23
    ailing
    -0.23
     diá
    -0.23
    :\/\/
    -0.23
     overwritten
    -0.23
    POSITIVE LOGITS
     distr
    0.28
    åĪ«è¯´
    0.28
    arta
    0.27
    éĻŁ
    0.27
    çļĦäºĭæĥħ
    0.26
    ä¸ĸçķĮä¸ĬæľĢ
    0.25
    é¡¹çĽ®å»ºè®¾
    0.24
    æĹı
    0.23
     MH
    0.23
    Âł
    0.23
    Activations Density 0.023%

    No Known Activations