© 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. 163010
    Prev
    Next
    INDEX
    Explanations

    Scientific, technical, court documents

    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
    æĸĹ
    -0.28
    éļĶ
    -0.28
    belie
    -0.26
    åĭĩæ°Ķ
    -0.25
    NewLabel
    -0.25
    onia
    -0.25
    ä»İå°ı
    -0.24
    bomb
    -0.24
    丹
    -0.24
    boxed
    -0.24
    POSITIVE LOGITS
    pré
    0.25
    atas
    0.25
    MEM
    0.24
     WA
    0.24
     wield
    0.24
     invest
    0.24
     polished
    0.23
    igar
    0.23
    atically
    0.23
    /release
    0.23
    Activations Density 0.136%

    No Known Activations