© 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. 161740
    Prev
    Next
    INDEX
    Explanations

    Guessing, expecting, thinking, knowing

    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
    Kyle
    -0.25
    èĦī
    -0.24
    ating
    -0.24
    gresql
    -0.24
    åįģåħŃ
    -0.23
    %%%
    -0.23
    èĦĪ
    -0.23
    âĪ
    -0.23
    toc
    -0.22
     terse
    -0.22
    POSITIVE LOGITS
    ONUS
    0.30
    ä¸įç¦ģ
    0.29
    addOn
    0.29
    éĤ£ä¸ªäºº
    0.27
    urous
    0.27
    isin
    0.27
    GetObject
    0.26
    ë¡ł
    0.26
    [loc
    0.25
    ä¸įèĩ³äºİ
    0.25
    Activations Density 0.015%

    No Known Activations