© 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. 161715
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    缩çŁŃ
    -0.27
    åIJ¯
    -0.25
    roots
    -0.25
    Ø£ÙĦ
    -0.24
    etty
    -0.24
    °C
    -0.23
     cháºŃm
    -0.23
     lm
    -0.23
     concept
    -0.23
     Gujar
    -0.23
    POSITIVE LOGITS
    ugged
    0.29
    æĬľãģij
    0.26
    asio
    0.25
    ogenesis
    0.25
    -guard
    0.24
    è¨Ģ
    0.24
    åŃĻåŃIJ
    0.24
    è¶Ĭ
    0.24
    atat
    0.24
    laus
    0.23
    Activations Density 0.002%

    No Known Activations