© 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. 48
    Prev
    Next
    INDEX
    Explanations

    presume

    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
    æ»ļåĬ¨
    -0.27
    缸åºĶ
    -0.26
    OfFile
    -0.25
    æľ¬èº«çļĦ
    -0.25
     pools
    -0.25
     Shapiro
    -0.24
    éļħ
    -0.24
    á¹£
    -0.24
    craper
    -0.23
    apur
    -0.23
    POSITIVE LOGITS
     acess
    0.24
    .qual
    0.24
    angler
    0.24
    ê²IJ
    0.24
    对å¾ħ
    0.23
    车载
    0.23
    è¿ĺä¸įæĺ¯
    0.23
    åĵĻ
    0.23
    ase
    0.22
    ilion
    0.22
    Activations Density 0.024%

    No Known Activations