© 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. 163113
    Prev
    Next
    INDEX
    Explanations

    Article summaries/extracts/titles

    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
     bufio
    -0.28
    ordes
    -0.26
     alike
    -0.26
    foil
    -0.25
    attery
    -0.25
    éĩijå¸ģ
    -0.25
     sublist
    -0.24
    .gold
    -0.24
    ften
    -0.24
    ÅĤó
    -0.24
    POSITIVE LOGITS
     ali
    0.27
     Ali
    0.27
    antino
    0.27
    åĴĮ社ä¼ļ
    0.26
     Vers
    0.26
    idon
    0.26
    åľ¨ä¸ŃåĽ½
    0.25
    (inter
    0.25
    Ali
    0.25
     provisions
    0.24
    Activations Density 0.012%

    No Known Activations