© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161922
    Prev
    Next
    INDEX
    Explanations

    Scientific/medical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿŁ
    -0.33
    ournal
    -0.26
     compét
    -0.26
    пан
    -0.25
    åĵĤ
    -0.24
    empre
    -0.24
    theast
    -0.24
    IJľç´¢
    -0.24
    ÑģÑĤва
    -0.24
     <->
    -0.23
    POSITIVE LOGITS
    å©Ĩ
    0.27
    icot
    0.26
     credited
    0.26
     pedestrian
    0.26
    cycl
    0.24
    filer
    0.24
    çŃīå¥ĸ
    0.24
    بÙĬÙĨ
    0.24
     balcon
    0.24
    åĥı
    0.23
    Activations Density 0.052%

    No Known Activations