© 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. 4-TRANSCODER-HP
    7. 267
    Prev
    Next
    INDEX
    Explanations

    keeping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?=
    -0.27
    onium
    -0.25
    uter
    -0.25
    ubern
    -0.25
     impress
    -0.24
    adget
    -0.24
     predis
    -0.24
     dozen
    -0.24
    iset
    -0.24
    intern
    -0.24
    POSITIVE LOGITS
    å§Ĭ妹
    0.25
    ness
    0.25
    AGO
    0.24
    æĪĸå¤ļæĪĸå°ij
    0.24
    两个人
    0.24
    ean
    0.24
    anny
    0.24
    IRC
    0.23
    ric
    0.23
    a
    0.22
    Activations Density 0.030%

    No Known Activations