© 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. 117
    Prev
    Next
    INDEX
    Explanations

    others

    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
    绣
    -0.28
    á»ı
    -0.28
     lim
    -0.26
    æĹ¥è®¯
    -0.26
     tallest
    -0.26
    .Serialize
    -0.25
    ERICA
    -0.25
    éĢļ
    -0.24
     iterate
    -0.24
    缸
    -0.24
    POSITIVE LOGITS
    æįº
    0.31
    é¹Ĭ
    0.27
     kra
    0.27
     cuckold
    0.26
     cooled
    0.26
     ingr
    0.25
    affected
    0.25
    æłī
    0.24
     mound
    0.24
    kü
    0.24
    Activations Density 0.282%

    No Known Activations