© 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. 162091
    Prev
    Next
    INDEX
    Explanations

    Semicolons

    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
    utto
    -0.26
    åİ»æİī
    -0.25
    ä¸į足以
    -0.25
    åı¦å¤ĸä¸Ģ个
    -0.25
    ï¼īãĢģ
    -0.25
    以åıĬ
    -0.24
    å¦Ĥæŀľæĺ¯
    -0.24
    ãĤ¥
    -0.24
    ãĢģ“
    -0.24
     Michaels
    -0.24
    POSITIVE LOGITS
    oso
    0.28
     lite
    0.27
    ichert
    0.26
    è°ı
    0.26
    æĿ¥çĶµ
    0.26
    失
    0.25
    VEST
    0.25
    searchModel
    0.25
    toBe
    0.24
    alytics
    0.24
    Activations Density 0.032%

    No Known Activations