© 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. 161951
    Prev
    Next
    INDEX
    Explanations

    Excerpts of text/dialog

    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
     via
    -0.26
    åIJİåĨį
    -0.24
     whatever
    -0.23
    Classes
    -0.22
    该æĢİä¹ĪåĬŀ
    -0.21
    &apos
    -0.21
    els
    -0.21
     porówn
    -0.21
     shortly
    -0.21
    æīįä¼ļ
    -0.21
    POSITIVE LOGITS
    æĪ·
    0.27
    ä¸īæľŁ
    0.27
    ONUS
    0.26
     corpor
    0.24
     hon
    0.24
    asan
    0.24
    æĪ¶
    0.23
    ASIC
    0.23
    ible
    0.23
    SAME
    0.22
    Activations Density 0.018%

    No Known Activations