© 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. 5
    Prev
    Next
    INDEX
    Explanations

    ow

    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
    æ³Ľ
    -0.29
    عÙĬÙĨ
    -0.26
    uil
    -0.25
    çīĪ
    -0.25
    orda
    -0.24
    squeeze
    -0.24
    çŀ»
    -0.24
    	usage
    -0.23
    hall
    -0.23
    hv
    -0.23
    POSITIVE LOGITS
    ä½ķå¿ħ
    0.26
    ä»İæł¹æľ¬
    0.25
    ki
    0.25
     Kerr
    0.25
    -work
    0.24
    ä»»ä½ķæŶåĢĻ
    0.24
    èĤīä½ĵ
    0.23
    heck
    0.23
    çŃĶåºĶ
    0.23
    egin
    0.23
    Activations Density 0.031%

    No Known Activations